Data science & analytics
Dashboards and predictive models that turn your data into decisions.
Overview
Most businesses already have the data to answer their biggest questions. I build the dashboards and models that answer them, and explain the results in plain language.
What I can build for you
Sales and revenue dashboards
Interactive Power BI or web dashboards showing live sales, revenue, customer segments and forecasts.
Customer churn prediction
AI flags customers likely to leave before they do, so you can reach out and keep them.
Demand forecasting
Predicts which products will sell next month from history, seasonality and trends.
Pricing optimisation
Analyses competitor pricing, demand and margins to recommend the best price for each product or service.
Tools I use
Related work
Full portfolioEjection fraction predictor
A machine learning model that predicts cardiac ejection fraction with 97% accuracy and explains each prediction.
- 97% prediction accuracy
- 1,600+ patient records
Credit underwriting model
An ML ensemble that replaced a rule-based loan approval system and improved accuracy by 18%.
- +18% accuracy over the rule-based system
- Ensemble of ML models
NBA analytics
An end-to-end pipeline that scraped 1,230+ NBA games and found statistically significant in-game patterns.
- 1,230+ games across 5 seasons
- 127 engineered features