Katkat
Back

Model Product Ranking

ShopifyMachine Learning Engineer · Onsite
MediumMachine Learning EngineerOnsiteMachine Learning

Last updated

This question evaluates understanding of end-to-end machine learning ranking systems, including label definition, feature engineering, model selection, training strategies, and offline/online evaluation.

You are building a machine learning model for product ranking in an e-commerce marketplace. Given a user, context, and a set of candidate products, rank the products so that the most relevant items appear first. Discuss the modeling approach: what data you would collect, how you would define labels, what features you would use, which models you would consider, how you would train the model, and how you would evaluate success offline and online.