Understanding SAM Forecasting Results
Overview
SAM provides comprehensive forecasting outputs designed to support both technical analysis and business decision-making. This guide explains how to interpret all 25+ metrics and use them effectively for strategic planning.
Primary Outputs
1. Forecast Data (CSV Export)
Professional CSV output with forecast data, accuracy metrics, and performance indicators for business analysis
Standardized 9-Column Format:
Week | Week_Ending_Date | Product_Category | Forecast_Model |
Actual_Values | Forecasted_Values | Root_Mean_Square_Error |
Absolute_Error | Cumulative_Absolute_Error
Key Features:
- Historical Fit: Shows how well models captured past patterns
- Validation Period: Out-of-sample accuracy assessment
- Future Forecasts: Predictions for your specified horizon
- Multiple Models: Compare performance across different algorithms
- Category Breakdown: Separate forecasts for each product/region/segment
2. Visual Analytics (Interactive Charts)
Chart Components:
- Actual vs Predicted Lines: Visual accuracy assessment
- Error Bands: Uncertainty visualization with confidence intervals
- Trend Indicators: Growth direction and magnitude
- Seasonal Patterns: Cyclical behavior identification
- Model Comparisons: Side-by-side performance visualization
3. Executive Summary (PDF Report)
Complete executive PDF report with model performance, visual analytics, business insights, and strategic recommendations
Multi-Page Professional Report:
- Title Page: Project overview and generation date
- Performance Summary: Model rankings and recommendations
- Visual Forecasts: All charts included with captions
- Business Insights: Key findings and strategic implications
- Technical Glossary: Metric definitions and interpretations
Understanding Accuracy Metrics
Primary Accuracy Indicators
RMSE (Root Mean Square Error)
What it measures: Overall prediction accuracy in original units
- Excellent: < 5% of data mean
- Good: 5-15% of data mean
- Fair: 15-30% of data mean
- Poor: > 30% of data mean
Business Interpretation:
Example: Sales RMSE = 1,200 units
• If average sales = 10,000 units → 12% error (Good)
• If average sales = 50,000 units → 2.4% error (Excellent)
MAPE (Mean Absolute Percentage Error)
What it measures: Average percentage error across all predictions
- Excellent: < 5%
- Good: 5-10%
- Fair: 10-20%
- Poor: > 20%
Business Interpretation:
MAPE = 8.5% means:
• Forecasts are typically within 8.5% of actual values
• For $100K revenue forecast, expect ±$8.5K accuracy
• Suitable for budgeting and planning purposes
Simplified Quality Ratings
Accuracy Assessment
Our AI automatically grades model performance:
- Excellent (MAPE < 5%): High confidence for strategic decisions
- Good (MAPE 5-10%): Reliable for operational planning
- Fair (MAPE 10-20%): Useful for directional guidance
- Poor (MAPE > 20%): Consider additional data or different approach
Confidence Levels
Risk assessment for forecast reliability:
- High: Low variability, consistent patterns, strong model fit
- Medium: Moderate uncertainty, acceptable for most planning
- Low: High variability, use with caution, consider ranges
Business Intelligence Metrics
Growth and Trend Analysis
Growth Rate Percentage
Calculation: (Forecast Mean - Historical Mean) / Historical Mean × 100 Business Use:
- Positive Growth: Expansion planning, resource allocation
- Negative Growth: Cost management, efficiency improvements
- Stable Growth: Maintenance mode, operational optimization
Forecast Trend Direction
- Increasing: Upward trajectory, growth opportunities
- Decreasing: Declining pattern, intervention needed
- Stable: Consistent performance, predictable planning
Historical vs Forecast Values
Compare past performance with future projections:
Historical Mean: 45,000 units/week
Forecast Mean: 52,000 units/week
Growth Rate: +15.6% (Strong growth expected)
SPYA Analysis (Same Period Year Ago)
SPYA Absolute Change
What it measures: Total difference between forecasted and same period last year Business Value: Seasonal comparison for business cycles
Example: Q4 forecast vs Q4 last year
SPYA Absolute Change: +125,000 units
Indicates stronger Q4 performance expected
SPYA Percentage Change
What it measures: Percentage growth vs same period last year Strategic Insights:
- Positive: Year-over-year growth
- Negative: Year-over-year decline
- Seasonal: Expected for cyclical businesses
Advanced Quality Metrics
Reliability and Confidence
Model Reliability Score (0-100)
Calculation: Accuracy-adjusted confidence measure
- 90-100: Extremely reliable, suitable for critical decisions
- 70-89: Good reliability, appropriate for most planning
- 50-69: Moderate reliability, use with additional validation
- < 50: Low reliability, consider alternative approaches
Forecast Stability Score
What it measures: Consistency of predictions across forecast horizon
- High Stability: Smooth, predictable forecasts
- Low Stability: Volatile predictions, higher uncertainty
- Business Impact: Planning complexity and risk assessment
Error Coefficient of Variation
Technical Measure: Standard deviation of errors / mean of actuals Business Interpretation:
- < 0.05: Very consistent performance
- 0.05-0.10: Acceptable variability
- > 0.10: High variability, consider forecast ranges
Data Quality Indicators
Trend Strength
Scale: 0-1, where higher values indicate stronger trends
- > 0.7: Strong trend, reliable for extrapolation
- 0.3-0.7: Moderate trend, good for medium-term planning
- < 0.3: Weak trend, focus on short-term forecasts
Seasonality Strength
Scale: 0-1, where higher values indicate stronger seasonal patterns
- > 0.7: Strong seasonality, plan for seasonal variations
- 0.3-0.7: Moderate seasonality, consider seasonal factors
- < 0.3: Weak seasonality, focus on trend and level
Model Performance Comparison
Model Rankings Table
Our executive summary includes a comprehensive comparison:
| Model | Accuracy Grade | MAPE | Reliability Score | Best Use Case |
|---|---|---|---|---|
| Prophet | Excellent | 4.2% | 94 | Strategic Planning |
| SARIMA | Good | 8.1% | 87 | Operational Forecasting |
| N-HiTS | Excellent | 3.8% | 96 | High-Stakes Decisions |
Recommendation Engine
Best Model Selection: Our AI recommends the optimal model based on:
- Accuracy Performance: Out-of-sample validation results
- Business Context: Forecast horizon and use case requirements
- Data Characteristics: Trend, seasonality, and quality factors
- Computational Efficiency: Processing time and resource requirements
Risk Assessment Framework
High Confidence Scenarios (Use forecasts directly)
- Accuracy Grade: Excellent
- Confidence Level: High
- MAPE < 5%
- Reliability Score > 90
Medium Confidence Scenarios (Use ranges)
- Accuracy Grade: Good/Fair
- Confidence Level: Medium
- Consider forecast ± error bounds
- Develop contingency plans
Low Confidence Scenarios (Directional guidance only)
- Accuracy Grade: Fair/Poor
- Confidence Level: Low
- Focus on trend direction
- Frequent re-forecasting recommended
AI-Generated Insights
Executive Summaries
What you get: Business-focused analysis for each forecast including:
- Performance assessment in business terms
- Key trends and growth opportunities
- Comparison to previous periods
- Strategic implications
Example:
"Product A shows 18% YoY growth with high reliability (87%). Clear seasonal patterns indicate March peak demand. Significant acceleration from Q4's 8% growth suggests successful market strategies requiring capacity validation."
Actionable Recommendations
Categories:
- Inventory Management: Stock level recommendations
- Marketing Strategy: Timing and targeting suggestions
- Capacity Planning: Resource allocation guidance
- Risk Management: Issue mitigation strategies
Interpreting Forecast Charts
Visual Elements
- Blue Line (Actual): Historical performance data
- Red Line (Forecast): Model predictions
- Orange Shading: Absolute error magnitude
- Confidence Bands: Upper and lower prediction bounds
Pattern Recognition
- Seasonal Peaks: Regular high/low cycles
- Trend Lines: Overall growth or decline direction
- Volatility: Consistency vs variability in patterns
- Break Points: Significant pattern changes
Business Insights
- Peak Planning: Prepare for seasonal demand spikes
- Trough Management: Optimize during low-demand periods
- Growth Trajectory: Long-term expansion or contraction
- Pattern Changes: Market shifts or business evolution
Common Pitfalls to Avoid
1. Over-Relying on Low Confidence Forecasts
- Problem: Major decisions on reliability scores under 70%
- Solution: Use for directional guidance only
2. Ignoring Seasonal Patterns
- Problem: Not accounting for seasonality
- Solution: Review seasonality strength, adjust plans
3. Misinterpreting Confidence Intervals
- Problem: Treating ranges as exact predictions
- Solution: Use for scenario planning
4. Not Validating Against Business Context
- Problem: Accepting forecasts misaligned with business changes
- Solution: Validate AI insights against business knowledge