Seasonal Index Forecast Adjustment
Statistical fallback layer using day-of-quarter index averages when ML model signals are insufficient.
Akash Sharma
Primary Owner
The Problem
Early in a quarter, ML models have limited QTD data to learn from. A statistically sound fallback was needed for low-data-quality early-quarter scenarios.
What Was Built
Built an average-index adjustment layer computing day-of-quarter historical indices (average pipeline completion percentage per day across prior quarters). Applied as a weighted fallback or blend with the ML forecast. Validated against real production data.
Business Impact
Improved early-quarter forecast stability and provided a robust statistical anchor validated against production pipeline data.
Related Revenue Forecasting Projects
Revenue Forecasting Platform
Production ML system predicting pipeline and booking outcomes at daily frequency across current and future quarters.
Time-Decay Forecast Smoothing
Dynamic adjustment layer that re-weights prior EOQ history by recency, capturing momentum and velocity signals closer to quarter end.
Model Explainability with SHAP
Dual-algorithm explainability infrastructure: SHAP for tree models, coefficient contribution for linear models, with BigQuery logging.