Opportunity Propensity Model
Predicts each opportunity's close likelihood per quarter, replacing static CRM probability fields with dynamically scored multi-quarter estimates.
Akash Sharma
Primary Owner
4
Quarter Horizons
Daily
Scoring Frequency
Overview
XGBoost Classifier trained on opportunity type, forecast category, stage timestamps, journey sequences, and close-date-relative temporal features. Scored daily across four quarter horizons. Feature selection via Feature Importance, Chi-squared, ANOVA F-test.
The problem
CRM probability fields are manually set and rarely updated, so they don't reflect actual close likelihood. Pipeline projections using these fields were systematically miscalibrated.
Results
Improved pipeline readiness projections by replacing static CRM probability fields with daily ML-scored multi-quarter conversion likelihoods.
Related Propensity & Scoring Projects
Account Propensity Model
Dual propensity scoring system assigning Base Fit (long-term ICP fit) and 3-Month (short-term conversion likelihood) scores to every account.
Lead Propensity Model
Scores each lead's conversion likelihood across four quarter horizons (CQ/NQ/NQ+1/NQ+2) using engagement patterns and journey sequences.
Multi-Horizon Account Propensity
Monthly-granularity refactor of the Account Propensity model, enabling month-level account prioritization alongside quarterly scores.