Opportunity Size Prediction
Predicts booking dollar value for leads and early-stage opportunities, enabling per-record expected value computation.
Akash Sharma
Primary Owner
Overview
XGBoost Regressor trained on account attributes, historical booking patterns, and product prediction inputs (from P14). Heuristic segment-average fallback for low-data scenarios. Feature selection via Information Value.
The problem
Many opportunities have missing or unreliable CRM amounts. Without predicted sizes, pipeline projection expected value calculations were inaccurate for early-stage records.
Results
Enabled reliable per-record expected value computation (propensity × size) in the Sales Pipeline Forecasting for all leads and opportunities, including those with missing amounts.
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.
Opportunity Propensity Model
Predicts each opportunity's close likelihood per quarter, replacing static CRM probability fields with dynamically scored multi-quarter estimates.