Construction project delay risk model

The brief

Project management offices want early warning of delays. Build a dataset of projects with features (type, size, contract, location, early progress), predict which ones will be delayed, and explain the main risks for each. Good looks like: a careful dataset, honest validation on unseen projects, and explanations project managers recognise.

What you will build

1. Build a project dataset from public data
2. Define delay and engineer early-warning features
3. Train classifiers with imbalance handling
4. Validate on unseen projects
5. Explain risks with SHAP

Free, open data to build it with

• Open Government Data Platform India ↗ Government of India

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.