Revenue ForecastingADA Asia2022 – 2024Production
Record Level Likelihood & Win Rate
ML-derived win rate methodology using per-record conversion likelihoods instead of binary counts for smoother, more accurate pipeline reporting.
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.
Tech Stack
PythonXGBoostBigQueryPySpark
Domain Tags
Win RateLikelihood MethodPipeline AnalyticsRevenue Metrics
Details
- Role
- Primary Owner
- Status
- Production
- Tier
- Tier 2
- Period
- 2022 – 2024
- Employment
- ADA Asia