Dataford
Interview QuestionsInterview GuidesExperiencesMock InterviewsPricing
Get started

Design an E-commerce Recommender

HardMachine Learning00:00
Practice interviewer
In session
5 left
00:00

Your question is Design an E-commerce Recommender. Take a moment with it on the right.

Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).

You need to log in / sign up to chat or submit.

Problem

Scenario

You are building a recommendation system for an e-commerce platform with a large catalog and repeat shoppers. The product team wants better personalized product suggestions across home page, product detail pages, and cart recovery surfaces, while still handling new users and new items.

Question

How would you design a recommendation system for an e-commerce platform?

Representative Dataset

Size·42M interaction events, 1.8M users, 320K productsTarget·Purchase within 24 hours after impressionFeatures·User, item, context, and user-item interaction featuresMissing data·User demographics and long-tail item metadata are partially missingClass balance·0.6% purchase rate, 3.8% click rate

What Good Looks Like

  • High Recall@K in retrieval so relevant items reach the ranker
  • Strong NDCG@10 and conversion lift in ranking
  • Good coverage across the catalog, not just popular items
  • Reasonable handling of cold-start users and products