Late delivery risk model

The brief

A supply chain team wants to warn customers and fix problems before orders are late. Predict late delivery risk at order time, avoid leaking information from after shipping, and explain the main causes. Good looks like: no leakage, metrics for the late class, and explanations operations managers recognise.

What you will build

1. Choose features known at order time only
2. Train gradient boosting and compare with a baseline
3. Evaluate recall and precision for late orders
4. Explain causes with SHAP
5. Suggest operational fixes

Free, open data to build it with

• DataCo smart supply chain ↗ Kaggle

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.