Remove simulated data creation - recommendations for new budgets now based on provided budget_amount and category knowledge only, not fake trends

app/main.py

@@ -219,11 +219,20 @@ async def check_and_get_recommendations(request: RecommendationRequest, month: O
         )
         
         if recommendations:
-            return RecommendationResponse(
-                has_previous_data=True,
-                recommendations=recommendations,
-                message=None
-            )
+            # Check if this is based on budget_amount only (no real historical data)
+            # If user doesn't have data but provided budget_amount, set has_previous_data=False
+            if not has_data and request.budget_amount:
+                return RecommendationResponse(
+                    has_previous_data=False,
+                    recommendations=recommendations,
+                    message="Recommendation generated based on provided budget amount. User does not have previous spending data for this category."
+                )
+            else:
+                return RecommendationResponse(
+                    has_previous_data=True,
+                    recommendations=recommendations,
+                    message=None
+                )
         else:
             # User has data but no recommendations generated (edge case)
             return RecommendationResponse(

app/smart_recommendation.py

@@ -377,44 +377,17 @@ class SmartBudgetRecommender:
         # Generate recommendation
         print(f"🔍 get_recommendation_for_category: Generating recommendation for category_name={category_name}, avg_expense={avg_expense}")
         
-        # If we only have budget_amount (no historical data), create simulated variation
-        # to help OpenAI make better recommendations based on category type
+        # If we only have budget_amount (no historical data), use it directly
+        # DO NOT create fake/simulated data - be honest with OpenAI that this is a new budget
         if using_budget_amount_only:
-            # Create simulated monthly values with realistic variation based on category
-            # This helps OpenAI understand spending patterns and make smarter recommendations
-            if "food" in category_name.lower() or "groceries" in category_name.lower() or "drinks" in category_name.lower():
-                # Food categories tend to have moderate variation
-                monthly_values = [
-                    avg_expense * 0.92,
-                    avg_expense * 0.96,
-                    avg_expense,
-                    avg_expense * 1.04,
-                    avg_expense * 1.08,
-                ]
-            elif "transport" in category_name.lower() or "travel" in category_name.lower():
-                # Transport can vary more
-                monthly_values = [
-                    avg_expense * 0.85,
-                    avg_expense * 0.95,
-                    avg_expense,
-                    avg_expense * 1.10,
-                    avg_expense * 1.15,
-                ]
-            else:
-                # Default: moderate variation
-                monthly_values = [
-                    avg_expense * 0.90,
-                    avg_expense * 0.95,
-                    avg_expense,
-                    avg_expense * 1.05,
-                    avg_expense * 1.10,
-                ]
-            
-            # Calculate std_dev from simulated values
-            mean = sum(monthly_values) / len(monthly_values)
-            variance = sum((x - mean) ** 2 for x in monthly_values) / len(monthly_values)
-            std_dev = variance ** 0.5
-            months_analyzed = len(monthly_values)
+            # Use the budget_amount as a single data point
+            # Don't create fake trends - OpenAI should recommend based on:
+            # 1. The budget amount provided
+            # 2. Category-specific knowledge
+            # 3. General inflation and best practices
+            monthly_values = [avg_expense]  # Single data point - no fake history
+            std_dev = avg_expense * 0.05  # Assume 5% typical variation for new budgets
+            months_analyzed = 1  # Only one month of data (the provided budget_amount)
         else:
             monthly_values = data.get("monthly_values", [avg_expense])
             std_dev = data.get("std_dev", 0.0)
@@ -1077,16 +1050,37 @@ class SmartBudgetRecommender:
         else:
             variability_level = "VERY LOW VARIABILITY - very predictable spending"
         
-        summary = (
-            f"Category: {category}\n"
-            f"Monthly spending values: [{history}]\n"
-            f"Average monthly spend: {avg_expense:,.2f}\n"
-            f"Standard deviation: {data['std_dev']:,.2f}\n"
-            f"Coefficient of variation: {cv:.1f}% ({variability_level})\n"
-            f"Number of months analyzed: {data['months_analyzed']}\n"
-            f"Total spending: {data.get('total', avg_expense * data['months_analyzed']):,.2f}\n"
-            f"Trend Analysis: {trend_analysis}\n"
-        )
+        # Check if this is a new budget (no historical data)
+        is_new_budget = len(monthly_values) == 1 and data.get('months_analyzed', 0) == 1
+        
+        if is_new_budget:
+            # This is a new budget - no historical data
+            summary = (
+                f"Category: {category}\n"
+                f"⚠️ IMPORTANT: This is a NEW BUDGET with NO historical spending data.\n"
+                f"The user has provided a budget amount of {avg_expense:,.2f} for this category.\n"
+                f"This is the ONLY data point available - there is NO spending history to analyze.\n\n"
+                f"Your recommendation should be based on:\n"
+                f"  1. The provided budget amount: {avg_expense:,.2f}\n"
+                f"  2. Category-specific knowledge (e.g., Food & Drinks inflation, Transport volatility)\n"
+                f"  3. General best practices (add 10-15% buffer for new budgets to account for variability)\n"
+                f"  4. Economic factors (inflation typically 2-5% annually, category-specific inflation)\n\n"
+                f"DO NOT reference fake trends or historical patterns - this is a new budget!\n"
+                f"Recommend a budget that accounts for typical variability and inflation for this category.\n"
+                f"For new budgets, typically recommend 10-15% increase from the provided amount to create a safety buffer.\n"
+            )
+        else:
+            # This is based on real historical data
+            summary = (
+                f"Category: {category}\n"
+                f"Monthly spending values: [{history}]\n"
+                f"Average monthly spend: {avg_expense:,.2f}\n"
+                f"Standard deviation: {data['std_dev']:,.2f}\n"
+                f"Coefficient of variation: {cv:.1f}% ({variability_level})\n"
+                f"Number of months analyzed: {data['months_analyzed']}\n"
+                f"Total spending: {data.get('total', avg_expense * data['months_analyzed']):,.2f}\n"
+                f"Trend Analysis: {trend_analysis}\n"
+            )
 
         prompt = (
             "You are an expert global personal finance coach with deep knowledge of:\n"