Data Science MasterClass (September) | 2 seats left

Design a Similar Items System

Design a Similar Items System

Free concept previewThe full case walkthrough and interview practice continue below.

Problem Formulation

Before you write a single line of model code, you need to nail down what the system is actually doing. Interviewers will probe this early, and candidates who skip straight to "train a two-tower model" without clarifying the product surface almost always back themselves into a corner.

Start by asking: is this a "customers who viewed this also viewed" widget, or a "similar items" widget on the product detail page? They sound identical but they're not. The first is collaborative by nature, built on session co-occurrence. The second can be answered purely from item content, which means it works even for brand-new listings. That distinction drives your entire model architecture.

Unlock Premium

Continue with the full applied walkthrough

Continue Design a Similar Items System with the applied case study, diagnostic checks, and the recommendation you would give a PM.

Work through the complete product case
Build the study design step by step
Interpret diagnostics and results
Practice a senior-level interview response

Realistic product cases inspired by

Google logo
Meta logo
Amazon logo
Netflix logo
Apple logo
Dan Lee

Built from a senior data scientist’s perspective

Learn what to check, what to say, and how to make the decision.

Unlock the applied lesson

Premium includes every course, applied case, and coding exercise.