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.
Akash Sharma
Primary Owner
Daily
Scoring Frequency
4 Tiers
Priority Buckets
Overview
Built two components: (1) Base Fit Propensity: XGBoost Classifier on firmographic features (industry, company size, region, existing customer flag) for long-term ICP fit. (2) 3-Month Propensity: XGBoost Classifier with engagement, funnel stage, activity, journey, and temporal features for short-term conversion likelihood. Feature selection via Feature Importance, Chi-squared test, ANOVA F-test. Heuristic fallback using historical conversion rates for low-data customers.
The problem
Sales and marketing teams worked with large account lists without systematic prioritization, dispersing effort across accounts with low conversion probability.
Results
Enabled High/Medium/Low/Deprioritize bucket assignment for systematic, daily account prioritization across enterprise B2B SaaS customers.
Related Propensity & Scoring Projects
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.
Opportunity Propensity Model
Predicts each opportunity's close likelihood per quarter, replacing static CRM probability fields with dynamically scored multi-quarter estimates.
Multi-Horizon Account Propensity
Monthly-granularity refactor of the Account Propensity model, enabling month-level account prioritization alongside quarterly scores.