Deal Win Probability Model
ML-derived win rate methodology using per-record conversion likelihoods instead of binary counts for smoother, more accurate pipeline reporting.
Akash Sharma
Primary Owner
The Problem
Standard win rate calculations used binary converted/not-converted counts, producing noisy rates with high variance. A smoother, probability-weighted method was needed.
What Was Built
Built a likelihood method computing win rates from ML-derived per-record conversion probabilities rather than binary outcomes. Enabled granular win rate reporting at the account, segment, and opportunity level.
Business Impact
Improved win rate metric accuracy and reduced variance in pipeline health reporting for GTM performance dashboards.
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.