Mini-project Logistics & Supply Chain Case Studio

Food delivery time predictor

Inspired by publicly reported work at Swiggy

Predict how long a food order will take to arrive from distance, traffic, weather and the rider.

The brief

Swiggy's tech blog has written about predicting delivery time even before an order is placed, and about how different cities and times of day behave. Using public Indian food-delivery data, predict delivery time, see where the model is worst (cities, weather, rush hours) and show the estimate a customer would see. Good looks like: error in minutes against a distance-only baseline, error broken down by city and time, and a checkout screen demo.

Read the case first

What Swiggy has said in public about this kind of work, on its own pages:

Make it your own

Predict a different delivery: medicine, groceries in 10 minutes, or tiffin boxes in your town. Decide what a promise should be (an average, or a time you meet 90% of the time) and judge the model on that.

AITeky has no link with Swiggy, which has not reviewed or endorsed this brief. The brief only draws on what the company has published, uses open data rather than its data, and is a learning exercise: don't present your project as Swiggy's work or system.

What you will build

Clean the data and compute distances
Build a distance-only baseline
Train a gradient-boosted model
Break down error by city, weather and hour
Show the estimate on a checkout screen demo

Free, open data to build it with

It takes a minute with your email. AiTeky Pass (₹999/month or ₹9,999/year) is free for your first 30 days.