Booking Prediction Model
Record-level ML system predicting booking likelihood and value, contributing to pipeline and booking projection.
Akash Sharma
Primary Owner
Weekend
MVP Build Time
Overview
Built using the ML Regression Framework: XGBoost Regressor and Classifier combination predicting booking likelihood and value at the record level. Evolved into the Product Prediction Model (P14) and established the reusable framework (P22).
The problem
Revenue teams needed per-record booking predictions for bottom-up forecasting, separate from the aggregate macro forecast.
Results
Provided per-record booking contribution estimates for the Sales Pipeline Forecasting and established the reusable modeling framework.
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.
Seasonal Index Forecast Adjustment
Statistical fallback layer using day-of-quarter index averages when ML model signals are insufficient.