Mini-project
Retail, E-commerce & Consumer Goods
Customer lifetime value predictor
Predict how much each customer will spend in the next six months from their order history.
The brief
An online retailer treats every customer the same. Predict each customer's spend in the next six months from their past orders, segment customers by value, and suggest how to treat each segment. Good looks like: a time-based setup with no leakage, a model that beats a simple average, and clear segments.
What you will build
- Build RFM features from past orders
- Set up a time-based training and test window
- Train regression models and compare with a baseline
- Segment customers by predicted value
- Suggest actions per segment
Free, open data to build it with
- Online Retail II ↗ UCI Machine Learning Repository
Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.