Mine Association Rules for a Grocery Retailer's Promo Strategy
Overview
What this challenge is about.
You receive 6 months of basket-level transaction data (around 22 million baskets, around 18,000 SKUs) plus a category taxonomy. Run association-rule mining (Apriori or FP-Growth) with appropriate support and confidence thresholds. Filter for lift greater than 1.3 and minimum support to keep rules generalizable. Cluster the rules into 10 thematically-coherent bundles and project the basket-size lift if each bundle is promoted. Deliverable is the rule set, the 10 bundles with rationale, and a one-pager for the buying team.
The Brief
What you'll do, and what you'll demonstrate.
Mine 6 months of basket data to surface 10 promo bundles with quantified expected basket-size lift.
Earning criteria — what you'll demonstrate
- Apply Apriori or FP-Growth at retail scale
- Set support/confidence/lift thresholds defensibly
- Cluster many small rules into a small set of buying-team-actionable bundles
- Project expected lift with explicit assumptions
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Data Scientist
Retail basket-mining is a classic data-scientist deliverable at any consumer goods or grocery company.
This challenge sharpens
- association-rules
- market-basket-analysis
- exploratory-data-analysis
Applied AI Scientist
Translating thousands of mined rules into ten executive-grade bundles mirrors the applied-scientist's role of compressing complexity for the business.
This challenge sharpens
- association-rules
- business-storytelling
- apriori
AI Product Manager
Owning the buying-team brief and projecting lift is the kind of analytical PM work AI PMs do constantly.
This challenge sharpens
- business-storytelling
- exploratory-data-analysis
- market-basket-analysis