{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "#**Multivariate Time Series Forecasting for Insurance Stock Using Macroeconomic Indicators**"
      ],
      "metadata": {
        "id": "K-L3TX0l06rJ"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Problem Statement**\n",
        "The objective of this project is to forecast the quarterly closing price of an insurance stock (AIG) using a multivariate time series model that incorporates macroeconomic indicators. This has applications in financial planning, risk management, and investment strategy."
      ],
      "metadata": {
        "id": "sG8oC6iE2A3g"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Step 1**\n",
        "\n",
        "**Data Acquisition**\n",
        "**AIG stock data** is fetched monthly from yfinance and then resampled to quarter‑end values, giving us our primary series, AIG.\n",
        "\n",
        "**Macroeconomic data (Real GDP, CPI, Unemployment Rate**) come from FRED and are aligned to the same quarter‑end dates.\n",
        "\n",
        "These 2 (AIG stock data and Macroeconomic data) are merged into one DataFrame, ensuring there are no missing entries."
      ],
      "metadata": {
        "id": "sIVT3eOa2G7I"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        " **Step 2: Exploratory Data Analysis (EDA)**\n",
        "Summary stats and missing values were checked.\n",
        "\n",
        "Line plots visualized seasonal and trend components.\n",
        "\n",
        "Seasonal Decomposition of the target (AIG).\n",
        "\n",
        "Correlation matrix revealed relationships between variables."
      ],
      "metadata": {
        "id": "CA-9Aymp45F7"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Step 3: Feature Engineering**\n",
        "Created lagged and rolling average features for each time series.\n",
        "\n",
        "Added lag1 and rolling mean (window=2) columns for both stock and macro features."
      ],
      "metadata": {
        "id": "SzlKNaFP5AAE"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Step 4: Stationarity & Differencing**\n",
        "Used the ADF test to check stationarity.\n",
        "\n",
        "Differenced non-stationary series using percentage change.\n",
        "\n",
        "Final set of features included both raw and differenced values."
      ],
      "metadata": {
        "id": "Yt55OF4r5Dw-"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Step 5: Scaling**\n",
        "StandardScaler was applied to the entire DataFrame to prepare for modeling."
      ],
      "metadata": {
        "id": "bSLn56e05HoI"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Step 6: Granger Causality Tests**\n",
        "\n",
        "Granger Causality Tests to identify macroeconomic variables that statistically cause changes in AIG.\n",
        "\n",
        "Correlation with Target measured feature relevance before modeling."
      ],
      "metadata": {
        "id": "LUjWzvkl5O3a"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Step 7: Train-Test Split**\n",
        "\n",
        "Split done chronologically (time-aware), not randomly."
      ],
      "metadata": {
        "id": "bt7y1DP85j9s"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Step 8: Model Training, forecasting and evaluation**\n",
        "\n",
        "Trained the data on VAR and XG-Boost"
      ],
      "metadata": {
        "id": "FfyYnKRb5q3H"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Summary**\n",
        "\n",
        "Built an end-to-end multivariate forecasting system.\n",
        "\n",
        "Combined statistical models (VAR) and machine learning models (XGBoost).\n",
        "\n",
        "Incorporated real-world macroeconomic context to improve prediction."
      ],
      "metadata": {
        "id": "-Ora1ny46NVX"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Importing Libraries"
      ],
      "metadata": {
        "id": "Pes5Rkjfw2Ai"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "1ltGql9XrLS_"
      },
      "outputs": [],
      "source": [
        "import pandas as pd , numpy as np , matplotlib.pyplot as plt , seaborn as sns, yfinance as yf\n",
        "from pandas_datareader import data as pdr"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Data Acquisition"
      ],
      "metadata": {
        "id": "f7LQWG0Xw45k"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#Download insurance stock (AIG) monthly prices and resample quarterly\n",
        "stock = yf.download('AIG', start='2015-01-01', end='2025-01-01', interval='1mo')\n",
        "\n",
        "# Extract closing price series and resample to quarter-end ('QE'), then rename\n",
        "close_df = stock['Close']\n",
        "\n",
        "# Resample at quarter end ('QE') and take last observation\n",
        "target_q = close_df.resample('QE').last()\n",
        "\n",
        "# Rename column to 'target'\n",
        "target_q.rename(columns={'Close': 'target'}, inplace=True)\n",
        "claims_df = target_q\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YV1mSQlHszKG",
        "outputId": "0b556eaa-e7f6-4baf-fc95-200110aa8247"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/tmp/ipython-input-2-2877806668.py:2: FutureWarning: YF.download() has changed argument auto_adjust default to True\n",
            "  stock = yf.download('AIG', start='2015-01-01', end='2025-01-01', interval='1mo')\n",
            "[*********************100%***********************]  1 of 1 completed\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "claims_df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 238
        },
        "id": "V8dAS3Z8tkM1",
        "outputId": "b6875c04-edfb-4117-f50b-569bdd132bbc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Ticker            AIG\n",
              "Date                 \n",
              "2015-03-31  42.543678\n",
              "2015-06-30  48.109562\n",
              "2015-09-30  44.311291\n",
              "2015-12-31  48.559849\n",
              "2016-03-31  42.541306"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-42645e8b-257e-4268-8419-dbf482c76c11\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th>Ticker</th>\n",
              "      <th>AIG</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Date</th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2015-03-31</th>\n",
              "      <td>42.543678</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-06-30</th>\n",
              "      <td>48.109562</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-09-30</th>\n",
              "      <td>44.311291</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-12-31</th>\n",
              "      <td>48.559849</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-03-31</th>\n",
              "      <td>42.541306</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-42645e8b-257e-4268-8419-dbf482c76c11')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-42645e8b-257e-4268-8419-dbf482c76c11 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-42645e8b-257e-4268-8419-dbf482c76c11');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    <div id=\"df-36f5dea0-3665-4c76-a37d-8a1001a552a9\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-36f5dea0-3665-4c76-a37d-8a1001a552a9')\"\n",
              "                title=\"Suggest charts\"\n",
              "                style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "      <script>\n",
              "        async function quickchart(key) {\n",
              "          const quickchartButtonEl =\n",
              "            document.querySelector('#' + key + ' button');\n",
              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "          try {\n",
              "            const charts = await google.colab.kernel.invokeFunction(\n",
              "                'suggestCharts', [key], {});\n",
              "          } catch (error) {\n",
              "            console.error('Error during call to suggestCharts:', error);\n",
              "          }\n",
              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "        }\n",
              "        (() => {\n",
              "          let quickchartButtonEl =\n",
              "            document.querySelector('#df-36f5dea0-3665-4c76-a37d-8a1001a552a9 button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "claims_df",
              "summary": "{\n  \"name\": \"claims_df\",\n  \"rows\": 40,\n  \"fields\": [\n    {\n      \"column\": \"Date\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2015-03-31 00:00:00\",\n        \"max\": \"2024-12-31 00:00:00\",\n        \"num_unique_values\": 40,\n        \"samples\": [\n          \"2019-12-31 00:00:00\",\n          \"2019-03-31 00:00:00\",\n          \"2018-12-31 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AIG\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12.143131955920873,\n        \"min\": 20.979589462280273,\n        \"max\": 75.76575469970703,\n        \"num_unique_values\": 40,\n        \"samples\": [\n          44.129329681396484,\n          36.32286071777344,\n          32.960330963134766\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Download macroeconomic indicators from FRED indicators\n",
        "\n",
        "macro_symbols = ['GDP', 'CPILFESL', 'UNRATE']  # Real GDP, CPI, Unemployment Rate\n",
        "macro_df = pdr.DataReader(macro_symbols, 'fred',\n",
        "                          start=claims_df.index.min(),\n",
        "                          end=claims_df.index.max())\n",
        "macro_df = macro_df.resample('QE').last()"
      ],
      "metadata": {
        "id": "Be2WJyoRuisD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "macro_df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 238
        },
        "id": "2SO8ukL9unqZ",
        "outputId": "3afc62de-bfcd-47b6-ee24-80dcef13fd12"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                  GDP  CPILFESL  UNRATE\n",
              "DATE                                   \n",
              "2015-06-30  18279.784   242.064     5.3\n",
              "2015-09-30  18401.626   243.316     5.0\n",
              "2015-12-31  18435.137   244.547     5.0\n",
              "2016-03-31  18525.933   245.913     5.0\n",
              "2016-06-30  18711.702   247.540     4.9"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-95dc259b-7ffd-4453-8d00-1b6334d62a7d\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>GDP</th>\n",
              "      <th>CPILFESL</th>\n",
              "      <th>UNRATE</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>DATE</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2015-06-30</th>\n",
              "      <td>18279.784</td>\n",
              "      <td>242.064</td>\n",
              "      <td>5.3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-09-30</th>\n",
              "      <td>18401.626</td>\n",
              "      <td>243.316</td>\n",
              "      <td>5.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-12-31</th>\n",
              "      <td>18435.137</td>\n",
              "      <td>244.547</td>\n",
              "      <td>5.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-03-31</th>\n",
              "      <td>18525.933</td>\n",
              "      <td>245.913</td>\n",
              "      <td>5.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-30</th>\n",
              "      <td>18711.702</td>\n",
              "      <td>247.540</td>\n",
              "      <td>4.9</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-95dc259b-7ffd-4453-8d00-1b6334d62a7d')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-95dc259b-7ffd-4453-8d00-1b6334d62a7d button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-95dc259b-7ffd-4453-8d00-1b6334d62a7d');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    <div id=\"df-02052057-e6bb-4e2b-8aab-6a96a59b806b\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-02052057-e6bb-4e2b-8aab-6a96a59b806b')\"\n",
              "                title=\"Suggest charts\"\n",
              "                style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "      <script>\n",
              "        async function quickchart(key) {\n",
              "          const quickchartButtonEl =\n",
              "            document.querySelector('#' + key + ' button');\n",
              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "          try {\n",
              "            const charts = await google.colab.kernel.invokeFunction(\n",
              "                'suggestCharts', [key], {});\n",
              "          } catch (error) {\n",
              "            console.error('Error during call to suggestCharts:', error);\n",
              "          }\n",
              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "        }\n",
              "        (() => {\n",
              "          let quickchartButtonEl =\n",
              "            document.querySelector('#df-02052057-e6bb-4e2b-8aab-6a96a59b806b button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "macro_df",
              "summary": "{\n  \"name\": \"macro_df\",\n  \"rows\": 39,\n  \"fields\": [\n    {\n      \"column\": \"DATE\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2015-06-30 00:00:00\",\n        \"max\": \"2024-12-31 00:00:00\",\n        \"num_unique_values\": 39,\n        \"samples\": [\n          \"2023-09-30 00:00:00\",\n          \"2024-06-30 00:00:00\",\n          \"2016-06-30 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"GDP\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3661.8905793590347,\n        \"min\": 18279.784,\n        \"max\": 29723.864,\n        \"num_unique_values\": 39,\n        \"samples\": [\n          27967.697,\n          29016.714,\n          18711.702\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"CPILFESL\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 25.44019725180067,\n        \"min\": 242.064,\n        \"max\": 323.296,\n        \"num_unique_values\": 39,\n        \"samples\": [\n          310.616,\n          318.343,\n          247.54\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"UNRATE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.4193619672451698,\n        \"min\": 3.5,\n        \"max\": 11.0,\n        \"num_unique_values\": 18,\n        \"samples\": [\n          5.3,\n          5.0,\n          3.7\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 2.3 Merge datasets on quarterly index\n",
        "\n",
        "df = pd.concat([claims_df, macro_df], axis=1).dropna()"
      ],
      "metadata": {
        "id": "tdZlF7WyuqQZ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "-bHkaxjqutgf",
        "outputId": "87264ecf-dcce-40d4-8f35-bdf7b2af3733"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                  AIG        GDP  CPILFESL  UNRATE\n",
              "2015-06-30  48.109562  18279.784   242.064     5.3\n",
              "2015-09-30  44.311291  18401.626   243.316     5.0\n",
              "2015-12-31  48.559849  18435.137   244.547     5.0\n",
              "2016-03-31  42.541306  18525.933   245.913     5.0\n",
              "2016-06-30  41.888119  18711.702   247.540     4.9"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-28903269-de1b-4952-9307-40d4f0250910\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>AIG</th>\n",
              "      <th>GDP</th>\n",
              "      <th>CPILFESL</th>\n",
              "      <th>UNRATE</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2015-06-30</th>\n",
              "      <td>48.109562</td>\n",
              "      <td>18279.784</td>\n",
              "      <td>242.064</td>\n",
              "      <td>5.3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-09-30</th>\n",
              "      <td>44.311291</td>\n",
              "      <td>18401.626</td>\n",
              "      <td>243.316</td>\n",
              "      <td>5.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015-12-31</th>\n",
              "      <td>48.559849</td>\n",
              "      <td>18435.137</td>\n",
              "      <td>244.547</td>\n",
              "      <td>5.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-03-31</th>\n",
              "      <td>42.541306</td>\n",
              "      <td>18525.933</td>\n",
              "      <td>245.913</td>\n",
              "      <td>5.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016-06-30</th>\n",
              "      <td>41.888119</td>\n",
              "      <td>18711.702</td>\n",
              "      <td>247.540</td>\n",
              "      <td>4.9</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-28903269-de1b-4952-9307-40d4f0250910')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-28903269-de1b-4952-9307-40d4f0250910 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-28903269-de1b-4952-9307-40d4f0250910');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    <div id=\"df-09644cd1-f88c-4a5b-9fc1-2b53e2fd328b\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-09644cd1-f88c-4a5b-9fc1-2b53e2fd328b')\"\n",
              "                title=\"Suggest charts\"\n",
              "                style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "      <script>\n",
              "        async function quickchart(key) {\n",
              "          const quickchartButtonEl =\n",
              "            document.querySelector('#' + key + ' button');\n",
              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "          try {\n",
              "            const charts = await google.colab.kernel.invokeFunction(\n",
              "                'suggestCharts', [key], {});\n",
              "          } catch (error) {\n",
              "            console.error('Error during call to suggestCharts:', error);\n",
              "          }\n",
              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "        }\n",
              "        (() => {\n",
              "          let quickchartButtonEl =\n",
              "            document.querySelector('#df-09644cd1-f88c-4a5b-9fc1-2b53e2fd328b button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 39,\n  \"fields\": [\n    {\n      \"column\": \"AIG\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12.267140126705568,\n        \"min\": 20.979589462280273,\n        \"max\": 75.76575469970703,\n        \"num_unique_values\": 39,\n        \"samples\": [\n          58.073543548583984,\n          72.29959869384766,\n          41.888118743896484\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"GDP\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3661.8905793590347,\n        \"min\": 18279.784,\n        \"max\": 29723.864,\n        \"num_unique_values\": 39,\n        \"samples\": [\n          27967.697,\n          29016.714,\n          18711.702\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"CPILFESL\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 25.44019725180067,\n        \"min\": 242.064,\n        \"max\": 323.296,\n        \"num_unique_values\": 39,\n        \"samples\": [\n          310.616,\n          318.343,\n          247.54\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"UNRATE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.4193619672451698,\n        \"min\": 3.5,\n        \"max\": 11.0,\n        \"num_unique_values\": 18,\n        \"samples\": [\n          5.3,\n          5.0,\n          3.7\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vDHFHZpmuu7A",
        "outputId": "21914b9a-6019-4d31-8bfc-7007460071d5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "DatetimeIndex: 39 entries, 2015-06-30 to 2024-12-31\n",
            "Freq: QE-DEC\n",
            "Data columns (total 4 columns):\n",
            " #   Column    Non-Null Count  Dtype  \n",
            "---  ------    --------------  -----  \n",
            " 0   AIG       39 non-null     float64\n",
            " 1   GDP       39 non-null     float64\n",
            " 2   CPILFESL  39 non-null     float64\n",
            " 3   UNRATE    39 non-null     float64\n",
            "dtypes: float64(4)\n",
            "memory usage: 1.5 KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 300
        },
        "id": "TmejIPg-uzTb",
        "outputId": "f93b634d-c3b4-4b6f-d74c-7926d26bd1df"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "             AIG           GDP    CPILFESL     UNRATE\n",
              "count  39.000000     39.000000   39.000000  39.000000\n",
              "mean   48.310683  22804.145359  274.468000   4.558974\n",
              "std    12.267140   3661.890579   25.440197   1.419362\n",
              "min    20.979597  18279.784000  242.064000   3.500000\n",
              "25%    43.522387  19814.019500  253.578000   3.750000\n",
              "50%    47.618820  21717.171000  266.020000   4.100000\n",
              "75%    52.283562  26038.901000  296.145000   4.950000\n",
              "max    75.765762  29723.864000  323.296000  11.000000"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-23bde102-c35b-4f3d-b0cf-e61d93464eaa\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>AIG</th>\n",
              "      <th>GDP</th>\n",
              "      <th>CPILFESL</th>\n",
              "      <th>UNRATE</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>39.000000</td>\n",
              "      <td>39.000000</td>\n",
              "      <td>39.000000</td>\n",
              "      <td>39.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>48.310683</td>\n",
              "      <td>22804.145359</td>\n",
              "      <td>274.468000</td>\n",
              "      <td>4.558974</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>12.267140</td>\n",
              "      <td>3661.890579</td>\n",
              "      <td>25.440197</td>\n",
              "      <td>1.419362</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>20.979597</td>\n",
              "      <td>18279.784000</td>\n",
              "      <td>242.064000</td>\n",
              "      <td>3.500000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>43.522387</td>\n",
              "      <td>19814.019500</td>\n",
              "      <td>253.578000</td>\n",
              "      <td>3.750000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>47.618820</td>\n",
              "      <td>21717.171000</td>\n",
              "      <td>266.020000</td>\n",
              "      <td>4.100000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>52.283562</td>\n",
              "      <td>26038.901000</td>\n",
              "      <td>296.145000</td>\n",
              "      <td>4.950000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>75.765762</td>\n",
              "      <td>29723.864000</td>\n",
              "      <td>323.296000</td>\n",
              "      <td>11.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-23bde102-c35b-4f3d-b0cf-e61d93464eaa')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-23bde102-c35b-4f3d-b0cf-e61d93464eaa button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-23bde102-c35b-4f3d-b0cf-e61d93464eaa');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    <div id=\"df-03de86f4-91e0-462e-abea-5bb6a46a63e5\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-03de86f4-91e0-462e-abea-5bb6a46a63e5')\"\n",
              "                title=\"Suggest charts\"\n",
              "                style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "      <script>\n",
              "        async function quickchart(key) {\n",
              "          const quickchartButtonEl =\n",
              "            document.querySelector('#' + key + ' button');\n",
              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "          try {\n",
              "            const charts = await google.colab.kernel.invokeFunction(\n",
              "                'suggestCharts', [key], {});\n",
              "          } catch (error) {\n",
              "            console.error('Error during call to suggestCharts:', error);\n",
              "          }\n",
              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "        }\n",
              "        (() => {\n",
              "          let quickchartButtonEl =\n",
              "            document.querySelector('#df-03de86f4-91e0-462e-abea-5bb6a46a63e5 button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 8,\n  \"fields\": [\n    {\n      \"column\": \"AIG\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 19.466954722933345,\n        \"min\": 12.267139952425264,\n        \"max\": 75.76576232910156,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          48.31068317706768,\n          47.61882019042969,\n          39.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"GDP\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 10488.473604499359,\n        \"min\": 39.0,\n        \"max\": 29723.864,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          22804.145358974358,\n          21717.171,\n          39.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"CPILFESL\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 115.62356349517783,\n        \"min\": 25.44019725180067,\n        \"max\": 323.296,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          274.468,\n          266.02,\n          39.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"UNRATE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12.417752832359948,\n        \"min\": 1.4193619672451698,\n        \"max\": 39.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          4.55897435897436,\n          4.1,\n          39.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#EDA"
      ],
      "metadata": {
        "id": "W119SxjPxJZV"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Plot series\n",
        "df.plot(subplots=True, figsize=(12, 8))\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 807
        },
        "id": "4cz2Ce9Au13o",
        "outputId": "28770a95-ef67-4a96-8091-b3e47a0f0124"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x800 with 4 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Explanation**\n",
        "\n",
        "AIG (Stock Price) fluctuated between 30 - 70 dollars, saw a sharp dip in 2020 due to COVID-19, followed by a steady post-pandemic recovery\n",
        "\n",
        "US real GDP shows a long-term upward trend, with a sharp dip in Q2 2020 from COVID-19, followed by a swift recovery and continued growth.\n",
        "\n",
        "Core CPI (CPILFESL) shows a smooth, steady rise, with a sharper post-2020 uptick reflecting underlying inflation pressures after the pandemic\n",
        "\n",
        "The unemployment rate showed a steady decline until a sharp spike in Q2 2020 due to the pandemic, followed by a rapid recovery to pre-pandemic levels by 2022."
      ],
      "metadata": {
        "id": "uCpu-3fWxjCE"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Decompose target series (period=4 for quarterly)\n",
        "from statsmodels.tsa.seasonal import seasonal_decompose\n",
        "result = seasonal_decompose(df['AIG'], model='additive', period=4)\n",
        "result.plot()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "1XXNg7knu9J8",
        "outputId": "23fe4afd-58ee-4bfb-d28c-6d452030c558"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 4 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Explanation**\n",
        "\n",
        "**Trend** : The stock's long-term trend was flat until 2019, dipped during the 2020 pandemic, then surged upward, signaling strong post-shock growth.\n",
        "\n",
        "**Seasonality**: The stock exhibits consistent seasonal patterns with small, periodic peaks every 4 quarters, likely driven by investor behavior, earnings cycles, or insurance seasonality\n",
        "\n",
        "**Residual**: The residuals fluctuate randomly around zero with some outliers in 2020, indicating minimal remaining structure after removing trend and seasonality."
      ],
      "metadata": {
        "id": "7QdAQScNyuZG"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(6,5))\n",
        "sns.heatmap(df.corr(), annot=True, fmt='.2f', cmap='coolwarm')\n",
        "plt.title('Correlation Matrix')\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 468
        },
        "id": "G_VAJPxbvFDr",
        "outputId": "80457b69-02f2-47a8-cf2a-b6b6c5411487"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 600x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Explanation**\n",
        "\n",
        "AIG - GDP shows strong positive relationship. As GDP grows, AIG stock tends to increase.\n",
        "\n",
        "AIG–CPILFESL also strongly positively correlated. Rising core inflation may reflect economic growth, benefitting insurers.\n",
        "\n",
        "AIG–UNRATE shows moderate negative correlation. As unemployment rises, AIG stock tends to fall—likely due to lower economic activity.\n",
        "\n",
        "**Summary**\n",
        "\n",
        "AIG stock is highly sensitive to macroeconomic trends—particularly economic growth (GDP), inflation (CPI), and employment.\n",
        "\n",
        "These variables are appropriate predictors for a multivariate time series model like VAR or XGBoost"
      ],
      "metadata": {
        "id": "kmZpODnhzXZB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#Preprocessing\n",
        "# Feature engineering: lags and rolling means\n",
        "\n",
        "for col in df.columns:\n",
        "    df[f'{col}_lag1'] = df[col].shift(1)\n",
        "    df[f'{col}_roll2'] = df[col].rolling(window=2).mean()\n",
        "df.dropna(inplace=True)"
      ],
      "metadata": {
        "id": "6o2LmoIiPnyN"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Checking Stationarity"
      ],
      "metadata": {
        "id": "LoWb-It_z1Be"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from statsmodels.tsa.stattools import adfuller\n",
        "\n",
        "def adf_test(series, name):\n",
        "    stat, p, *_ = adfuller(series)\n",
        "    print(f'{name}: ADF stat={stat:.3f}, p={p:.3f}')\n",
        "    return p\n",
        "\n",
        "# Identify which base series need differencing\n",
        "base_cols = ['AIG', 'GDP', 'CPILFESL', 'UNRATE']\n",
        "pvals = {col: adf_test(df[col], col) for col in base_cols}\n",
        "\n",
        "# Decide differencing: p-value >= 0.05 indicates non-stationarity\n",
        "diff_needed = [col for col, p in pvals.items() if p >= 0.05]\n",
        "print('Differencing needed for:', diff_needed)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WI4M5mxwPw3C",
        "outputId": "79fd308f-77d6-4123-bc87-392f90741977"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "AIG: ADF stat=-1.311, p=0.624\n",
            "GDP: ADF stat=0.950, p=0.994\n",
            "CPILFESL: ADF stat=2.086, p=0.999\n",
            "UNRATE: ADF stat=-2.901, p=0.045\n",
            "Differencing needed for: ['AIG', 'GDP', 'CPILFESL']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Applying differencing"
      ],
      "metadata": {
        "id": "5Oxt7LTSz4Oj"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Apply first-order differencing only to non-stationary series\n",
        "diff_cols = []\n",
        "for col in base_cols:\n",
        "    if col in diff_needed:\n",
        "        df[f'{col}_diff'] = df[col] - df[col].shift(1)\n",
        "        diff_cols.append(f'{col}_diff')\n",
        "    else:\n",
        "        # Keep stationary series as-is (use original)\n",
        "        diff_cols.append(col)\n",
        "\n",
        "df.dropna(inplace=True)"
      ],
      "metadata": {
        "id": "galCD4jGPy1u"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Scalling Using Standard Scaler"
      ],
      "metadata": {
        "id": "MMsQ3Il6z7VU"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.preprocessing import StandardScaler\n",
        "scaler = StandardScaler()\n",
        "df_scaled = pd.DataFrame(scaler.fit_transform(df), index=df.index, columns=df.columns)"
      ],
      "metadata": {
        "id": "coXy4GBuQWmk"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Checking Casuality"
      ],
      "metadata": {
        "id": "hDEjMpNX0AAO"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from statsmodels.tsa.stattools import grangercausalitytests\n",
        "\n",
        "print(\"\"\"\n",
        "--- Granger Causality Test Results ---\"\"\")\n",
        "for col in diff_cols:\n",
        "    if col != f'{\"AIG\"}_diff':\n",
        "        # print(f\"Does {col} Granger-cause {\"AIG\"}_diff?\")\n",
        "        grangercausalitytests(df[[f'{\"AIG\"}_diff', col]], maxlag=4, verbose=True)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-h3zZgr0O6jB",
        "outputId": "f1219da6-ef69-468b-eb41-ce6c6132a4ef"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "--- Granger Causality Test Results ---\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 1\n",
            "ssr based F test:         F=1.7627  , p=0.1934  , df_denom=33, df_num=1\n",
            "ssr based chi2 test:   chi2=1.9230  , p=0.1655  , df=1\n",
            "likelihood ratio test: chi2=1.8734  , p=0.1711  , df=1\n",
            "parameter F test:         F=1.7627  , p=0.1934  , df_denom=33, df_num=1\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 2\n",
            "ssr based F test:         F=1.7263  , p=0.1952  , df_denom=30, df_num=2\n",
            "ssr based chi2 test:   chi2=4.0280  , p=0.1335  , df=2\n",
            "likelihood ratio test: chi2=3.8126  , p=0.1486  , df=2\n",
            "parameter F test:         F=1.7263  , p=0.1952  , df_denom=30, df_num=2\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 3\n",
            "ssr based F test:         F=1.2195  , p=0.3217  , df_denom=27, df_num=3\n",
            "ssr based chi2 test:   chi2=4.6069  , p=0.2030  , df=3\n",
            "likelihood ratio test: chi2=4.3204  , p=0.2289  , df=3\n",
            "parameter F test:         F=1.2195  , p=0.3217  , df_denom=27, df_num=3\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 4\n",
            "ssr based F test:         F=0.7064  , p=0.5954  , df_denom=24, df_num=4\n",
            "ssr based chi2 test:   chi2=3.8853  , p=0.4218  , df=4\n",
            "likelihood ratio test: chi2=3.6731  , p=0.4521  , df=4\n",
            "parameter F test:         F=0.7064  , p=0.5954  , df_denom=24, df_num=4\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 1\n",
            "ssr based F test:         F=1.6335  , p=0.2101  , df_denom=33, df_num=1\n",
            "ssr based chi2 test:   chi2=1.7820  , p=0.1819  , df=1\n",
            "likelihood ratio test: chi2=1.7393  , p=0.1872  , df=1\n",
            "parameter F test:         F=1.6335  , p=0.2101  , df_denom=33, df_num=1\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 2\n",
            "ssr based F test:         F=1.1736  , p=0.3231  , df_denom=30, df_num=2\n",
            "ssr based chi2 test:   chi2=2.7383  , p=0.2543  , df=2\n",
            "likelihood ratio test: chi2=2.6365  , p=0.2676  , df=2\n",
            "parameter F test:         F=1.1736  , p=0.3231  , df_denom=30, df_num=2\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 3\n",
            "ssr based F test:         F=0.9597  , p=0.4259  , df_denom=27, df_num=3\n",
            "ssr based chi2 test:   chi2=3.6257  , p=0.3048  , df=3\n",
            "likelihood ratio test: chi2=3.4451  , p=0.3280  , df=3\n",
            "parameter F test:         F=0.9597  , p=0.4259  , df_denom=27, df_num=3\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 4\n",
            "ssr based F test:         F=0.8019  , p=0.5359  , df_denom=24, df_num=4\n",
            "ssr based chi2 test:   chi2=4.4105  , p=0.3533  , df=4\n",
            "likelihood ratio test: chi2=4.1397  , p=0.3874  , df=4\n",
            "parameter F test:         F=0.8019  , p=0.5359  , df_denom=24, df_num=4\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 1\n",
            "ssr based F test:         F=0.8517  , p=0.3628  , df_denom=33, df_num=1\n",
            "ssr based chi2 test:   chi2=0.9292  , p=0.3351  , df=1\n",
            "likelihood ratio test: chi2=0.9174  , p=0.3382  , df=1\n",
            "parameter F test:         F=0.8517  , p=0.3628  , df_denom=33, df_num=1\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 2\n",
            "ssr based F test:         F=2.2085  , p=0.1274  , df_denom=30, df_num=2\n",
            "ssr based chi2 test:   chi2=5.1533  , p=0.0760  , df=2\n",
            "likelihood ratio test: chi2=4.8075  , p=0.0904  , df=2\n",
            "parameter F test:         F=2.2085  , p=0.1274  , df_denom=30, df_num=2\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 3\n",
            "ssr based F test:         F=1.3529  , p=0.2782  , df_denom=27, df_num=3\n",
            "ssr based chi2 test:   chi2=5.1111  , p=0.1638  , df=3\n",
            "likelihood ratio test: chi2=4.7616  , p=0.1901  , df=3\n",
            "parameter F test:         F=1.3529  , p=0.2782  , df_denom=27, df_num=3\n",
            "\n",
            "Granger Causality\n",
            "number of lags (no zero) 4\n",
            "ssr based F test:         F=0.6169  , p=0.6547  , df_denom=24, df_num=4\n",
            "ssr based chi2 test:   chi2=3.3929  , p=0.4943  , df=4\n",
            "likelihood ratio test: chi2=3.2296  , p=0.5202  , df=4\n",
            "parameter F test:         F=0.6169  , p=0.6547  , df_denom=24, df_num=4\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.11/dist-packages/statsmodels/tsa/stattools.py:1556: FutureWarning: verbose is deprecated since functions should not print results\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.11/dist-packages/statsmodels/tsa/stattools.py:1556: FutureWarning: verbose is deprecated since functions should not print results\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.11/dist-packages/statsmodels/tsa/stattools.py:1556: FutureWarning: verbose is deprecated since functions should not print results\n",
            "  warnings.warn(\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Explanation**\n",
        "\n",
        "Granger Causality doesn’t imply true causality, but rather tells us whether past values of one time series help predict another\n",
        "\n",
        "None of the tested macro indicators (GDP, CPI, UNRATE) Granger-cause AIG’s stock price at a statistically significant level (p < 0.05)"
      ],
      "metadata": {
        "id": "8a9UHSXX0s_A"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Train test split"
      ],
      "metadata": {
        "id": "iFjsDSY501tn"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Step 7: Train-Test Split & Cross-Validation\n",
        "# ================================\n",
        "from sklearn.model_selection import TimeSeriesSplit\n",
        "ticker = \"AIG\"\n",
        "# Step 7: Train-Test Split for VAR\n",
        "train = df_scaled.loc[:'2022-12-31']\n",
        "test = df_scaled.loc['2023-01-01':]\n",
        "\n",
        "# Use only the differenced (stationary) columns\n",
        "train_diff = train[diff_cols]\n",
        "test_diff = test[diff_cols]\n",
        "\n"
      ],
      "metadata": {
        "id": "po1VlRIKQeSf"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Model Training [VAR]"
      ],
      "metadata": {
        "id": "5Ya_nZyL04pa"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from statsmodels.tsa.api import VAR\n",
        "# Fit VAR model\n",
        "model = VAR(endog=train_diff)\n",
        "\n",
        "# Select optimal lag order\n",
        "lag_order_results = model.select_order(maxlags=4)\n",
        "print(lag_order_results.summary())\n",
        "opt_lag = lag_order_results.aic\n",
        "print(\"Selected lag based on AIC:\", opt_lag)\n",
        "\n",
        "\n",
        "# Fit the model with optimal lag\n",
        "results = model.fit(opt_lag)\n",
        "\n",
        "# Forecast\n",
        "forecast = results.forecast(train_diff.values[-opt_lag:], steps=len(test_diff))\n",
        "forecast_df = pd.DataFrame(forecast, index=test_diff.index, columns=diff_cols)\n"
      ],
      "metadata": {
        "id": "4Nl1pI9iQuaU",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "cef0f6d6-3e0c-4349-fcfd-887a5b98591d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            " VAR Order Selection (* highlights the minimums) \n",
            "=================================================\n",
            "      AIC         BIC         FPE         HQIC   \n",
            "-------------------------------------------------\n",
            "0      0.7005      0.8955       2.015      0.7545\n",
            "1      -3.614      -2.638     0.02755      -3.343\n",
            "2      -4.527      -2.772     0.01237      -4.041\n",
            "3      -5.602     -3.067*   0.005792*      -4.899\n",
            "4     -5.890*      -2.575    0.009117     -4.971*\n",
            "-------------------------------------------------\n",
            "Selected lag based on AIC: 4\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "forecast_df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 300
        },
        "collapsed": true,
        "id": "iT4RtzjiRQUs",
        "outputId": "8e4c723c-07e1-4d92-b1f0-a087c2507a1c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "            AIG_diff  GDP_diff  CPILFESL_diff    UNRATE\n",
              "2023-03-31 -1.944537  1.835633       2.285828 -2.073042\n",
              "2023-06-30  0.105112 -1.030189       0.552985 -1.183762\n",
              "2023-09-30 -0.685905  0.873217       1.090670 -1.598088\n",
              "2023-12-31 -1.214340 -0.504888       1.211717 -0.952064\n",
              "2024-03-31  0.547228  0.034643      -0.280343 -0.943777\n",
              "2024-06-30 -1.213736  1.014186       1.443448 -1.655000\n",
              "2024-09-30 -0.506274 -1.092932      -0.505760 -0.874059\n",
              "2024-12-31 -0.330800  0.231920       0.482767 -0.763152"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-54fc18ff-c112-41a9-862e-5f23284a63c6\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>AIG_diff</th>\n",
              "      <th>GDP_diff</th>\n",
              "      <th>CPILFESL_diff</th>\n",
              "      <th>UNRATE</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2023-03-31</th>\n",
              "      <td>-1.944537</td>\n",
              "      <td>1.835633</td>\n",
              "      <td>2.285828</td>\n",
              "      <td>-2.073042</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2023-06-30</th>\n",
              "      <td>0.105112</td>\n",
              "      <td>-1.030189</td>\n",
              "      <td>0.552985</td>\n",
              "      <td>-1.183762</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2023-09-30</th>\n",
              "      <td>-0.685905</td>\n",
              "      <td>0.873217</td>\n",
              "      <td>1.090670</td>\n",
              "      <td>-1.598088</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2023-12-31</th>\n",
              "      <td>-1.214340</td>\n",
              "      <td>-0.504888</td>\n",
              "      <td>1.211717</td>\n",
              "      <td>-0.952064</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2024-03-31</th>\n",
              "      <td>0.547228</td>\n",
              "      <td>0.034643</td>\n",
              "      <td>-0.280343</td>\n",
              "      <td>-0.943777</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2024-06-30</th>\n",
              "      <td>-1.213736</td>\n",
              "      <td>1.014186</td>\n",
              "      <td>1.443448</td>\n",
              "      <td>-1.655000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2024-09-30</th>\n",
              "      <td>-0.506274</td>\n",
              "      <td>-1.092932</td>\n",
              "      <td>-0.505760</td>\n",
              "      <td>-0.874059</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2024-12-31</th>\n",
              "      <td>-0.330800</td>\n",
              "      <td>0.231920</td>\n",
              "      <td>0.482767</td>\n",
              "      <td>-0.763152</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-54fc18ff-c112-41a9-862e-5f23284a63c6')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-54fc18ff-c112-41a9-862e-5f23284a63c6 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-54fc18ff-c112-41a9-862e-5f23284a63c6');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    <div id=\"df-27f71e8e-7449-4784-aa66-f449bf369994\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-27f71e8e-7449-4784-aa66-f449bf369994')\"\n",
              "                title=\"Suggest charts\"\n",
              "                style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "      <script>\n",
              "        async function quickchart(key) {\n",
              "          const quickchartButtonEl =\n",
              "            document.querySelector('#' + key + ' button');\n",
              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "          try {\n",
              "            const charts = await google.colab.kernel.invokeFunction(\n",
              "                'suggestCharts', [key], {});\n",
              "          } catch (error) {\n",
              "            console.error('Error during call to suggestCharts:', error);\n",
              "          }\n",
              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "        }\n",
              "        (() => {\n",
              "          let quickchartButtonEl =\n",
              "            document.querySelector('#df-27f71e8e-7449-4784-aa66-f449bf369994 button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "  <div id=\"id_5f560f19-e621-421d-a8ce-3bd3d1eabe9d\">\n",
              "    <style>\n",
              "      .colab-df-generate {\n",
              "        background-color: #E8F0FE;\n",
              "        border: none;\n",
              "        border-radius: 50%;\n",
              "        cursor: pointer;\n",
              "        display: none;\n",
              "        fill: #1967D2;\n",
              "        height: 32px;\n",
              "        padding: 0 0 0 0;\n",
              "        width: 32px;\n",
              "      }\n",
              "\n",
              "      .colab-df-generate:hover {\n",
              "        background-color: #E2EBFA;\n",
              "        box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "        fill: #174EA6;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate:hover {\n",
              "        background-color: #434B5C;\n",
              "        box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "        filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "        fill: #FFFFFF;\n",
              "      }\n",
              "    </style>\n",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('forecast_df')\"\n",
              "            title=\"Generate code using this dataframe.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_5f560f19-e621-421d-a8ce-3bd3d1eabe9d button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('forecast_df');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "forecast_df",
              "summary": "{\n  \"name\": \"forecast_df\",\n  \"rows\": 8,\n  \"fields\": [\n    {\n      \"column\": \"AIG_diff\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.7963536912128677,\n        \"min\": -1.944537421300318,\n        \"max\": 0.5472278707228639,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          0.10511195351624125,\n          -1.2137355848463223,\n          -1.944537421300318\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"GDP_diff\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.0347240697277702,\n        \"min\": -1.092932054403522,\n        \"max\": 1.8356332246514167,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          -1.0301885228957062,\n          1.0141855588726085,\n          1.8356332246514167\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"CPILFESL_diff\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.9186756404738565,\n        \"min\": -0.5057604967129858,\n        \"max\": 2.2858284153847803,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          0.5529851043886886,\n          1.4434477560676136,\n          2.2858284153847803\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"UNRATE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.46715486138967355,\n        \"min\": -2.073041520700105,\n        \"max\": -0.7631524698767125,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          -1.1837623524151777,\n          -1.6549997200067834,\n          -2.073041520700105\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 112
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "actual_df = df_scaled[[\"AIG_diff\", \"GDP_diff\",\"CPILFESL_diff\", \"UNRATE\"]]"
      ],
      "metadata": {
        "id": "K3bVxnNoRYMV"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "# Plot each column\n",
        "\n",
        "plt.figure(figsize=(12, 5))\n",
        "plt.plot(actual_df.index, actual_df[\"AIG_diff\"], label='Actual', color='blue')\n",
        "plt.plot(forecast_df.index, forecast_df[\"AIG_diff\"], label='Forecast', color='orange', linestyle='--')\n",
        "plt.title(f'Actual vs Forecast for AIG_diff')\n",
        "plt.xlabel('Date')\n",
        "plt.ylabel(\"AIG_diff\")\n",
        "plt.legend()\n",
        "plt.grid(True)\n",
        "plt.tight_layout()\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 507
        },
        "id": "tEKTxxBPTSH-",
        "outputId": "efa97d88-8438-4e29-b58b-d4306ca40525"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x500 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import mean_absolute_error, mean_squared_error\n",
        "# print('MAE:', mean_absolute_error(actual_df[\"AIG_diff\"].iloc[-8:], forecast_df[\"AIG_diff\"]))\n",
        "aligned_actual = actual_df[\"AIG_diff\"].loc[forecast_df.index]\n",
        "print('MAE:', mean_absolute_error(aligned_actual, forecast_df[\"AIG_diff\"]))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QpNwJcylWnMl",
        "outputId": "0b0475ac-8a82-4efa-8283-4281e3c60105"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "MAE: 0.7644475236904735\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Using XG-Boost"
      ],
      "metadata": {
        "id": "r2_OCebN1Ykr"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#Benchmarking with XGBoost\n",
        "\n",
        "ticker = \"AIG\"\n",
        "from xgboost import XGBRegressor\n",
        "from lightgbm import LGBMRegressor\n",
        "from sklearn.model_selection import TimeSeriesSplit\n",
        "\n",
        "# Use lag/rolling features as predictors\n",
        "X_cols = [col for col in df.columns if '_lag' in col or '_roll' in col]\n",
        "y_col = f'{ticker}_diff'\n",
        "\n",
        "X_train = train[X_cols]\n",
        "y_train = train[y_col]\n",
        "X_test = test[X_cols]\n",
        "y_test = test[y_col]\n",
        "\n",
        "\n"
      ],
      "metadata": {
        "id": "PM5OdkQgRB_J"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "**TimeSeriesSplit** is a cross-validation strategy specifically designed for time series data, where the assumption of independent and identically distributed samples does not hold. It respects the temporal order of observations, essential when forecasting future values based on past data."
      ],
      "metadata": {
        "id": "4UgG5-HQTbzg"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Evaluating Metrics\n",
        "\n",
        "\n",
        "from sklearn.model_selection import TimeSeriesSplit\n",
        "from sklearn.metrics import mean_squared_error, mean_absolute_error\n",
        "from xgboost import XGBRegressor\n",
        "import numpy as np\n",
        "\n",
        "tscv = TimeSeriesSplit(n_splits=3)\n",
        "model = XGBRegressor()\n",
        "\n",
        "fold_rmse = []\n",
        "y_true_all = []\n",
        "y_pred_all = []\n",
        "\n",
        "for train_idx, val_idx in tscv.split(X_train):\n",
        "    X_t, X_v = X_train.iloc[train_idx], X_train.iloc[val_idx]\n",
        "    y_t, y_v = y_train.iloc[train_idx], y_train.iloc[val_idx]\n",
        "\n",
        "    model.fit(X_t, y_t)\n",
        "    preds = model.predict(X_v)\n",
        "\n",
        "    fold_rmse.append(np.sqrt(mean_squared_error(y_v, preds)))\n",
        "    y_true_all.extend(y_v)\n",
        "    y_pred_all.extend(preds)\n",
        "\n",
        "print('--- XGBoost (Raw % Change) ---')\n",
        "print('Average Fold RMSE:', np.mean(fold_rmse))\n",
        "print('Overall MAE:', mean_absolute_error(y_true_all, y_pred_all))\n",
        "print('Overall RMSE:', np.sqrt(mean_squared_error(y_true_all, y_pred_all)))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gwTleoBybdr6",
        "outputId": "1ed1696d-5f60-4580-9377-40e9ca458cf4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--- XGBoost (Raw % Change) ---\n",
            "Average Fold RMSE: 0.9045371164614275\n",
            "Overall MAE: 0.6345718363868207\n",
            "Overall RMSE: 0.922077769815283\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "plt.figure(figsize=(8,4))\n",
        "plt.plot(y_true_all, label='Actual')\n",
        "plt.plot(y_pred_all, label='XGBoost Prediction')\n",
        "plt.legend(); plt.title('Cross-Validated Raw % Change'); plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 391
        },
        "id": "MhUFi5vqp4RI",
        "outputId": "1706324c-1616-42f5-f124-9f2edd246323"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x400 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Hyper Parameter tuning"
      ],
      "metadata": {
        "id": "ZuF5nNEO14Ss"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import GridSearchCV, TimeSeriesSplit\n",
        "from xgboost import XGBRegressor\n",
        "import numpy as np\n",
        "\n",
        "#  model\n",
        "xgb = XGBRegressor(objective='reg:squarederror', random_state=42)\n",
        "\n",
        "#parameter grid\n",
        "param_grid = {\n",
        "    'n_estimators': [50, 100, 200],\n",
        "    'max_depth': [2, 3, 4],\n",
        "    'learning_rate': [0.01, 0.05, 0.1],\n",
        "    'subsample': [0.8, 1.0],\n",
        "    'colsample_bytree': [0.8, 1.0]\n",
        "}\n",
        "\n",
        "# TimeSeriesSplit\n",
        "tscv = TimeSeriesSplit(n_splits=3)\n",
        "\n",
        "#Set up GridSearchCV\n",
        "grid_search = GridSearchCV(\n",
        "    estimator=xgb,\n",
        "    param_grid=param_grid,\n",
        "    cv=tscv,\n",
        "    scoring='neg_root_mean_squared_error',\n",
        "    verbose=1,\n",
        "    n_jobs=-1\n",
        ")\n",
        "\n",
        "\n",
        "grid_search.fit(X_train, y_train)\n",
        "\n",
        "# Parameters\n",
        "print(\"Best Parameters:\", grid_search.best_params_)\n",
        "print(\"Best RMSE:\", -grid_search.best_score_)\n",
        "\n",
        "# best model\n",
        "best_model = grid_search.best_estimator_\n",
        "y_pred_best = best_model.predict(X_test)\n",
        "\n",
        "#Evaluate on test set\n",
        "from sklearn.metrics import mean_squared_error, mean_absolute_error\n",
        "\n",
        "print(\"Test MAE:\", mean_absolute_error(y_test, y_pred_best))\n",
        "print(\"Test RMSE:\", np.sqrt(mean_squared_error(y_test, y_pred_best)))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_GRn-sobanyk",
        "outputId": "b99b259c-2b26-4321-c2bb-e35bdb4a4db3"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Fitting 3 folds for each of 108 candidates, totalling 324 fits\n",
            "Best Parameters: {'colsample_bytree': 1.0, 'learning_rate': 0.05, 'max_depth': 4, 'n_estimators': 200, 'subsample': 1.0}\n",
            "Best RMSE: 0.8194041605855737\n",
            "Test MAE: 0.8803066680851019\n",
            "Test RMSE: 0.9659637757684871\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(8,4))\n",
        "plt.plot(y_test.values, label='Actual')\n",
        "plt.plot(y_pred_best, label='Tuned XGBoost Prediction')\n",
        "plt.title('Tuned XGBoost: Prediction vs Actual (% Change)')\n",
        "plt.legend(); plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 391
        },
        "id": "334mhKjtqKVd",
        "outputId": "7dc381c6-3e2b-46d2-bd09-9d3146155b5a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x400 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Metric Evaluation**\n",
        "\n",
        "Cross-validated RMSE improved after tuning, which indicates better generalization during training.\n",
        "\n",
        "However, test MAE and RMSE increased slightly, which may suggest mild overfitting or underfitting in the final test fold.\n",
        "\n",
        "Overall, the tuned model performs more consistently across folds, even if slightly less accurate on final unseen data."
      ],
      "metadata": {
        "id": "m1bHBwZO3C4_"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Checking Feature Importance"
      ],
      "metadata": {
        "id": "xF5BFLl22VkF"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from xgboost import plot_importance\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "\n",
        "_ = plot_importance(best_model.best_estimator_ if hasattr(best_model, 'best_estimator_') else best_model)\n",
        "plt.title(\"Feature Importance - XGBoost\")\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 472
        },
        "id": "Axo1Lcwoqb4E",
        "outputId": "b6506633-4734-4204-ae37-e6b0f210730f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Explanation**\n",
        "\n",
        "Lag features dominate the model is learning from recent historical values more than smoothed ones.\n",
        "\n",
        "Macroeconomic indicators (GDP, Unemployment) provide contextual strength, but stock-specific lags matter more.\n",
        "\n",
        "CPI seems least important in the current window, possibly due to its indirect link to short-term stock movements."
      ],
      "metadata": {
        "id": "9st6OBsz3aaS"
      }
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "8_SpxnyC3cNd"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}