Search query to product predictor
Inspired by publicly reported work at Best Buy
Predict which product a shopper wants from what they typed into an electronics store search box.
The brief
Best Buy once released real search queries from its mobile site for a public data-mining challenge: what shoppers typed, and which product they then looked at. Predict the product from the query, starting with simple text matching and improving with a model. Good looks like: top-5 accuracy against a text-match baseline, an error analysis of misspellings and vague queries, and a small search demo.
Read the case first
What Best Buy has said in public about this kind of work, on its own pages:
Make it your own
Do it for an Indian electronics or mobile shop: Hinglish queries, local brand names and model numbers. Write 200 test queries of your own and report how the model does on them.
AITeky has no link with Best Buy, 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 Best Buy's work or system.
What you will build
- Explore queries, products and clicks
- Build a text-match baseline
- Clean queries (spelling, model numbers, brands)
- Train a classifier or embedding search
- Measure top-5 accuracy and analyse errors
- Build a search demo
Free, open data to build it with
Sign up free to get the data and links
It takes a minute with your email. AiTeky Pass (₹999/month or ₹9,999/year) is free for your first 30 days.