Career Work

All Projects

25 production ML systems built across 4+ years — every project here shipped to production and was owned end-to-end, from research through maintenance.

Revenue Forecasting · 7Pipeline Intelligence · 3Marketing Science · 3Propensity & Scoring · 7Data Engineering · 3Platform & Infrastructure · 2
Revenue Forecasting
Production

Revenue Forecasting Platform

Production ML system predicting pipeline and booking outcomes at daily frequency across current and future quarters.

PythonXGBoostRidge Regression+7
View Case Study →
Marketing Science
Production

Marketing Mix Modeling Platform

Full-stack marketing attribution and budget optimization platform—from raw channel spend to response curves and scenario planning.

PythonBayesianRidgescikit-learn+6
View Case Study →
Marketing Science
Production

Multi-Touch Attribution System

Probabilistic multi-touch attribution using Markov Chain removal-effect modeling — crediting each channel based on its actual influence on conversion probability across the full customer journey.

PythonMarkov Chainscikit-learn+1
View Case Study →
Pipeline Intelligence
Production

Full Pipeline Projection Engine

Central projection system integrating 8+ ML model families into a single daily revenue forecast across four quarter horizons.

PythonXGBoostscikit-learn+3
View Case Study →
Pipeline Intelligence
Production

Demand Generation Potential Model

Estimates pipeline contribution from opportunities not yet visible in the CRM — the 'unseen' quarter contribution.

PythonXGBoostscikit-learn+1
View Case Study →
Pipeline Intelligence
Production

Walk-In Pipeline Projection

Regression-based estimate of within-quarter pipeline creation from sources not visible at quarter start.

PythonXGBoostscikit-learn+1
View Case Study →
Propensity & Scoring
Production

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.

PythonXGBoostscikit-learn+3
View Case Study →
Propensity & Scoring
Production

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.

PythonXGBoostscikit-learn+1
View Case Study →
Propensity & Scoring
Production

Opportunity Propensity Model

Predicts each opportunity's close likelihood per quarter, replacing static CRM probability fields with dynamically scored multi-quarter estimates.

PythonXGBoostscikit-learn+1
View Case Study →
Propensity & Scoring
Production

Account Propensity X Month

Monthly-granularity refactor of the Account Propensity model, enabling month-level account prioritization alongside quarterly scores.

PythonXGBoostscikit-learn+1
View Case Study →
Revenue Forecasting
Production

Time-Decay Forecast Adjustment

Dynamic adjustment layer that re-weights prior EOQ history by recency, capturing momentum and velocity signals closer to quarter end.

PythonXGBoostscikit-learn+1
View Case Study →
Revenue Forecasting
Production

Average-Index Forecast Adjustment

Statistical fallback layer using day-of-quarter index averages when ML model signals are insufficient.

Pythonscikit-learnBigQuery
View Case Study →
Revenue Forecasting
Production

Forecast Explainability & SHAP Logging

Dual-algorithm explainability infrastructure — SHAP for tree models, coefficient contribution for linear models — with BigQuery logging.

PythonSHAPTreeExplainer+3
View Case Study →
Revenue Forecasting
Production

Configurable Multi-Model ML Framework

30+ parameter framework for runtime algorithm selection, feature group configuration, and model stacking across the forecasting platform.

PythonXGBoostLightGBM+4
View Case Study →
Marketing Science
Production

Campaign Performance Prediction Engine

Two-stage system predicting campaign pipeline potential before launch and monitoring active campaigns daily.

PythonXGBoostscikit-learn+1
View Case Study →
Data Engineering
Production

Revenue Metrics Pipeline Migration

Migrated the revenue metrics pipeline from single-machine pandas to distributed PySpark, resolving critical implementation bugs to unblock daily ML scoring.

PySparkSpark SQLGCP Dataproc+2
View Case Study →
Data Engineering
Production

Campaign Entity Resolution

Fuzzy matching + BERT embedding system to deduplicate and resolve campaign entities across CRM and marketing platform data sources.

PythonSplinkBERT Embeddings+2
View Case Study →
Data Engineering
Production

Smart Filter Parser & SQL Generation

Metadata-driven SQL generation system translating user-defined filter configurations into executable BigQuery queries.

PythonSQLBigQuery+1
View Case Study →
Platform & Infrastructure
Production

Generic Regressor Framework

Reusable ML regression framework standardizing feature engineering, training, validation, and scoring — adopted as the baseline for all subsequent platform models.

PythonXGBoostRidge+4
View Case Study →
Platform & Infrastructure
Production

Model Metric Dashboard

Internal ML governance dashboard tracking train/test MAPE, MAE, RMSE, and classification metrics across all deployed platform models.

PythonBigQueryDashboard
View Case Study →
Propensity & Scoring
Production

Product Prediction Model

Predicts which products are likely associated with a lead conversion, improving downstream opportunity size estimation.

PythonXGBoostscikit-learn+1
View Case Study →
Propensity & Scoring
Production

Opportunity Size Prediction

Predicts booking dollar value for leads and early-stage opportunities, enabling per-record expected value computation.

PythonXGBoostscikit-learn+1
View Case Study →
Propensity & Scoring
Production

Customer Segmentation Clustering

Unsupervised clustering model grouping accounts by firmographic and behavioral attributes for GTM targeting.

Pythonscikit-learnBigQuery
View Case Study →
Revenue Forecasting
Production

Booking Prediction Model

Record-level ML system predicting booking likelihood and value, contributing to pipeline and booking projection.

PythonXGBoostscikit-learn+1
View Case Study →
Revenue Forecasting
Production

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.

PythonXGBoostBigQuery+1
View Case Study →