Major project
Logistics & Supply Chain
Late-delivery risk and supply-chain control tower
Predict which orders will arrive late and build a control-tower view for the logistics team.
The brief
A distributor promises delivery dates it often misses, and customers leave. Build a model that predicts late delivery when an order is placed, find the routes, modes and products that cause delays, and give the logistics team a control-tower dashboard. Good looks like: late orders flagged early enough to act, the main causes quantified, and a dashboard with what-if options.
What you will build
- Explore delivery delays by market, shipping mode and product
- Engineer order-time features (no data from after shipping)
- Train and compare late-delivery classifiers
- Quantify the causes of delay
- Build the control-tower dashboard with alerts
- Recommend process changes with expected impact
Free, open data to build it with
- DataCo Smart Supply Chain ↗ Kaggle
- Brazilian E-Commerce by Olist ↗ 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.