How do I approach ML System Design interview questions?

ML System Design questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master ml system design interviews.

What difficulty level is this interview question?

This is a medium difficulty ML System Design question, commonly asked during Technical Screen rounds at Uber.

What role is this question designed for?

This question is commonly asked for Data Scientist candidates at Uber during technical interviews.

Design Uber Eats Restaurant Recommendations | Uber Interview Question

Design Uber Eats Restaurant Recommendations

Last updated: May 2, 2026

Quick Overview

This question evaluates a candidate's ability in end-to-end machine learning system design for personalized restaurant recommendations in a food-delivery marketplace, assessing competencies such as candidate generation, ranking, feature engineering, labeling, offline and online evaluation, real-time serving, cold-start handling, exploration/exploitation, and marketplace constraint management. Such problems are commonly asked to evaluate architectural thinking and trade-off analysis between model quality and operational constraints; the category is ML System Design and the level of abstraction spans both conceptual understanding and practical application.

Uber

Apr 30, 2026, 12:00 AM

Data Scientist

Technical Screen

ML System Design

Design a restaurant recommendation system for the Uber Eats home page.

A user opens the Uber Eats app and should see a ranked feed of restaurants available near their delivery location. Your design should cover:

Product goals and success metrics.
Data sources and logging.
Candidate generation and ranking.
Useful user, restaurant, context, and marketplace features.
Training labels and model choices.
Offline evaluation and online experimentation.
Cold-start handling for new users and new restaurants.
Exploration versus exploitation.
Real-time serving architecture and latency constraints.
Marketplace constraints such as delivery time, restaurant capacity, promotions, fairness, and user experience.
Monitoring and failure modes after launch.

Solution

Show

Comments (0)

Loading comments...

Browse More Questions

More ML System Design•More Uber•More Data Scientist•Uber Data Scientist•Uber ML System Design•Data Scientist ML System Design