Delivery time predictor

The brief

Customers want an accurate delivery time, not a guess. Predict delivery time from distance (computed from coordinates), traffic, weather, vehicle and order details, compare regression models, and show which factors matter. Good looks like: careful feature engineering, honest validation, and errors reported in minutes.

What you will build

1. Compute distance from pickup and drop coordinates
2. Engineer time, traffic and weather features
3. Train linear and gradient-boosted models
4. Evaluate errors in minutes
5. Explain the main drivers

Free, open data to build it with

• Amazon delivery dataset ↗ Kaggle
• Food delivery dataset ↗ 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.