Study · 03 — Lab
B2B customer churn prediction
A model to anticipate which wholesale customers are about to stop buying.
The problem
Losing a B2B customer becomes obvious only once they are gone.
What I built
Out-of-time validation, RFM features with trend, logistic regression against Random Forest and LightGBM, and interpretation with SHAP.
What changed
The model returns a risk ranking together with the reasons behind each case.
Tools
- Python
- LightGBM
- SHAP