Projects
Evidence of how I think, build, analyse, and learn.
Use this page for serious case studies. Replace every placeholder result with a verified outcome and link to the underlying work.
Purchase Propensity Model
A series walking through building a purchase propensity model end to end — from the business problem to model design, data preparation, and beyond.
Part 1Purchase Propensity Modeling: A Beginner’s Guide to Predicting Customer Purchase ProbabilitiesPart 1 of 6 series to explain the problem statement and concept behind Purchase Propensity Model.Part 2Model Designing: Observation Window,Populations and Data LeakagePart 2 of 6 series to explain the problem statement and concept behind Purchase Propensity Model.Part 3Data Preparation: Cleaning, Sessionizing, and Feature EngineeringPart 3 of 6. How to clean web clickstream data, build sessions, create the target and engineer features that carry purchase intent.Part 4Model Training: Logistic Regression, Random Forest, and LightGBMPart 4 of 6. Splitting the data by time, training three models of increasing complexity, and reading the first comparison table.Part 5Model Testing and Targeting: Lift, Calibration, and the Campaign AudiencePart 5 of 6. Judging the model on the untouched test set, then turning its scores into a real campaign audience with business rules and a holdout.Part 6 Beyond Propensity Scores: uplift, production, and keeping a model honest over timePart 6 of 6. Propensity versus uplift on a simulated randomised campaign, a production architecture, and how to monitor a model for drift.