Mini-project Retail, E-commerce & Consumer Goods Case Studio

Weekly store sales forecast with holidays

Inspired by publicly reported work at Walmart

Forecast weekly sales by store and department, and show how holidays and markdowns change them.

The brief

Walmart's technology team has written about forecasting demand so the right products are in the right place, especially around holidays. Using sales data Walmart released for a public competition, forecast weekly sales by store and department and measure how holidays and markdowns change them. Good looks like: a seasonal baseline, a model that beats it on a time-based test, holiday weeks analysed separately, and a forecast dashboard.

Read the case first

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

Make it your own

Make the holidays Indian: Diwali, Eid, Pongal and the wedding season, with sales from a local shop or a public Indian retail dataset. Show which festival weeks your model gets most wrong and why.

AITeky has no link with Walmart, 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 Walmart's work or system.

What you will build

Explore weekly sales by store, department and holiday
Build a seasonal naive baseline
Train a gradient-boosted or time-series model
Evaluate on the last months with holiday weeks weighted
Build a forecast dashboard for a store manager

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.