Predicting the Likelihood to Purchase a Financial Product Following a Direct Marketing Campaign

A data-driven tool to identify the best candidates for a marketing campaign and optimize it.

Predictive State Propensity Subclassification (PSPS): A causal deep learning algoritm in TensorFlow keras

Propensity model to predict a customer's likelihood of purchasing a product from an online store based on past behaviour

A repo with functions for building various COMs and GCOMs quickly.

Propensity Modelling and RFM Analysis to predict users' likelihood of making a purchase.

The feature of interest is whether or not a customer buys a caravan insurance, based on socio-demographic factors and ownership of other insurance policies; and to build profile of a typical customer.

Website Traffic & Conversion Prediction: Regression and churn analysis for a UK heat pump company to optimize the conversion funnel using user behavior data.

Product propensity on 461k x 488 anonymized banking features: 7-model bake-off with OOF stacking, ROC-AUC 0.741

Sales prediction for a segment of product.

ML model to predict which customers are likely to purchase a Mutual Fund

A predictive analytics project developed during my MSc AI at BSBI. This project implements a binary classification pipeline to predict customer purchase behavior based on demographic and interaction data. It covers the full ML lifecycle: from Exploratory Data Analysis (EDA) and feature engineering to model selection and performance benchmarking.

Propensity modeling project for ShopNow to predict 30‑day purchase likelihood, compare Ridge/Lasso/Random Forest/XGBoost, and optimize marketing profit using a cost‑based evaluation framework.

A self-hosted BigQuery ML pipeline that predicts purchase propensity from GA4 events and pushes the result back to GA4 as a user property via the Measurement Protocol. Built for Google Ads remarketing. Consent-aware, cost-capped, and production-hardened.

Customer response modeling, segmentation, and propensity-based campaign targeting strategy.

Predicting customer conversion likelihood for bank term deposit campaigns using a calibrated propensity model to optimise telemarketing outreach.

Causal inference analysis using Propensity Score Matching to measure competitor impact on store sales. Isolates true treatment effect from confounding factors with statistical rigor.

Explores the relationship between population demographics, various crime rates, and shall carry gun laws across different regions of the United States between 1977-1999 using a propensity weighted mixed linear effects model.