api

app.py

@@ -525,37 +525,162 @@ async def get_customer_analysis(customer_id: str):
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
             detail=f"Error processing request: {str(e)}"
         )
-class CardRecommendation(BaseModel):
-    name: str
-    annual_fee: float
-    rewards_rate: float
-    benefits: str
-
-class InvestmentRecommendation(BaseModel):
-    type: str
-    risk_level: str
-    expected_return: float
-    min_investment: float
-
-class RealEstateRecommendation(BaseModel):
-    type: str
-    location: str
-    price: float
-    monthly_payment: float
-    roi_potential: float
-
-class FinancialAnalysisResponse(BaseModel):
-    monthly_avg_spend: float
-    spend_trend: float
-    credit_score_range: str
-    credit_score_change: str
-    investment_potential: float
-    spending_categories: List[Dict[str, float]]
-    spending_insights: List[str]
-    recent_transactions: List[Dict[str, Any]]
-    card_recommendations: List[CardRecommendation]
-    investment_recommendations: List[InvestmentRecommendation]
-    real_estate_recommendations: List[RealEstateRecommendation]
-    financial_health_score: int
-    action_items: List[str]
+@app.get("/financial-recommendations/{customer_id}")
+async def get_financial_recommendations(customer_id: str):
+    """
+    Get hyper-personalized financial recommendations for a customer
+    
+    Parameters:
+    - customer_id: The ID of the customer
+    
+    Returns:
+    - JSON object containing personalized financial recommendations and insights
+    """
+    try:
+        # Validate customer
+        if customer_id not in customer_profiles['Customer_Id'].unique():
+            raise HTTPException(
+                status_code=status.HTTP_404_NOT_FOUND,
+                detail="Customer not found"
+            )
+        
+        # Get customer profile data
+        customer_profile = customer_profiles[customer_profiles['Customer_Id'] == customer_id].iloc[0]
+        
+        # Get purchase history
+        customer_purchases = purchase_history[purchase_history['Customer_Id'] == customer_id]
+        
+        # Get social sentiment data
+        customer_sentiment = customer_Media[customer_Media['Customer_Id'] == customer_id]
+        
+        # Calculate financial metrics
+        total_spent = customer_purchases['Amount (In Dollars)'].sum()
+        avg_transaction = customer_purchases['Amount (In Dollars)'].mean()
+        purchase_frequency = len(customer_purchases) / (
+            (customer_purchases['Purchase_Date'].max() - customer_purchases['Purchase_Date'].min()).days + 1
+        )
+        
+        # Denormalize age and income
+        age = customer_profile['Age'] * scaler.scale_[0] + scaler.mean_[0]
+        income = customer_profile['Income per year (in dollars)'] * scaler.scale_[1] + scaler.mean_[1]
+        
+        # Calculate spending ratio
+        spending_ratio = (total_spent / income) * 100 if income > 0 else 0
+        
+        # Generate personalized recommendations
+        recommendations = {
+            "investment_recommendations": [],
+            "savings_recommendations": [],
+            "budget_recommendations": [],
+            "risk_assessment": "",
+            "action_items": []
+        }
+        
+        # Investment recommendations based on age and income
+        if age < 30:
+            recommendations["investment_recommendations"].extend([
+                "Consider starting a retirement account with aggressive growth funds",
+                "Look into low-cost index funds for long-term growth",
+                "Build an emergency fund of 3-6 months expenses"
+            ])
+        elif age < 50:
+            recommendations["investment_recommendations"].extend([
+                "Diversify investment portfolio with mix of stocks and bonds",
+                "Consider real estate investment opportunities",
+                "Maximize retirement contributions"
+            ])
+        else:
+            recommendations["investment_recommendations"].extend([
+                "Focus on preservation of capital",
+                "Consider dividend-paying stocks",
+                "Review retirement withdrawal strategy"
+            ])
+        
+        # Savings recommendations based on spending ratio
+        if spending_ratio > 70:
+            recommendations["savings_recommendations"].extend([
+                "Critical: Reduce monthly expenses",
+                "Implement 50/30/20 budgeting rule",
+                "Identify and cut non-essential spending"
+            ])
+        elif spending_ratio > 50:
+            recommendations["savings_recommendations"].extend([
+                "Look for additional saving opportunities",
+                "Consider automated savings transfers",
+                "Review subscription services"
+            ])
+        else:
+            recommendations["savings_recommendations"].extend([
+                "Maintain current saving habits",
+                "Consider increasing investment contributions",
+                "Look into tax-advantaged savings options"
+            ])
+        
+        # Budget recommendations based on purchase patterns
+        category_spending = customer_purchases.groupby('Category')['Amount (In Dollars)'].sum()
+        top_spending_categories = category_spending.nlargest(3)
+        
+        recommendations["budget_recommendations"].extend([
+            f"Highest spending in {cat}: ${amount:.2f}" 
+            for cat, amount in top_spending_categories.items()
+        ])
+        
+        # Risk assessment based on sentiment and spending patterns
+        recent_sentiment = customer_sentiment.sort_values('Timestamp', ascending=False)['Sentiment_Score'].mean()
+        if recent_sentiment < -0.2:
+            risk_level = "Conservative"
+        elif recent_sentiment > 0.2:
+            risk_level = "Moderate"
+        else:
+            risk_level = "Balanced"
+            
+        recommendations["risk_assessment"] = f"Based on your profile and behavior: {risk_level} risk tolerance"
+        
+        # Generate action items
+        recommendations["action_items"] = [
+            {
+                "priority": "High",
+                "action": "Review and adjust monthly budget",
+                "impact": "Immediate",
+                "timeline": "Next 30 days"
+            },
+            {
+                "priority": "Medium",
+                "action": "Rebalance investment portfolio",
+                "impact": "Long-term",
+                "timeline": "Next 90 days"
+            },
+            {
+                "priority": "Low",
+                "action": "Schedule financial planning review",
+                "impact": "Strategic",
+                "timeline": "Next 6 months"
+            }
+        ]
+        
+        return {
+            "customer_id": customer_id,
+            "financial_summary": {
+                "total_spent": float(total_spent),
+                "average_transaction": float(avg_transaction),
+                "spending_ratio": float(spending_ratio),
+                "purchase_frequency": float(purchase_frequency)
+            },
+            "risk_profile": {
+                "age_group": "Young" if age < 30 else "Middle-aged" if age < 50 else "Senior",
+                "income_bracket": "Low" if income < 50000 else "Medium" if income < 100000 else "High",
+                "risk_tolerance": risk_level
+            },
+            "recommendations": recommendations,
+            "analysis_timestamp": datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+        }
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Error processing financial recommendations for customer {customer_id}: {str(e)}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=f"Error processing request: {str(e)}"
+        )