Design a movie recommendation system like Netflix
PremiumML systemMedium
- Two tower model
- Candidate generation
- Learning to rank
Quick answer
This ML system interview question asks you to design a movie recommendation system like Netflix. Aim for a design that turns data into useful predictions in production, then explain the data, training, serving and monitoring. Interviewers want to see how you frame the problem, measure success and keep the model healthy after launch.
The problem
Design a movie recommendation system like Netflix: choose and order the titles in the "Top picks for you" row on each member's home page. The hard parts are learning from implicit signals (plays, not ratings), giving new titles a fair chance and optimising for members staying subscribed rather than for clicks.
Members rarely rate titles, so the signals are plays, how much of a title they watched, and titles they scrolled past. A title that looks exciting but is abandoned after 2 minutes is a bad recommendation even though it got a play.
What must a movie recommendation system like Netflix do?
- Personal row: Return the top 40 titles for a member's "Top picks" row, ordered by predicted value.
- Fresh context: Reflect what the member watched in the last session when the home page reloads.
How well must it do it?
- Latency: The row is ready within 150 ms p99 of a home page request.
- Long-term value: Optimise for viewing hours and retention, not raw play count.
What scale should you design for?
Use these numbers in your estimates.
The scale numbers unlock with this questionUnlock
Key concepts
- Two tower model
- Candidate generation
- Learning to rank
- Implicit feedback
- Cold start
- Exploration
How you’ll practise
- Problem framing
- Data and labels
- Features and model
- Training and evaluation
- Serving and monitoring
- Wrap-up
Lala, personalized to you, gives a hint when you ask and reviews your design when you are ready.
What do interviewers look for?
In any ML system design round.
- Frames the product goal as a clear ML problem
- Defines offline and online success metrics
- Explains where the data and labels come from
- Separates training from serving and keeps features consistent
- Plans for drift, retraining and rollbacks
- Weighs model quality against latency and cost
Questions people ask about this interview question
- Which design type is this question?
- It is an ML system question. You design a movie recommendation system like Netflix and explain your choices the way you would in an interview.
- Is this question asked at entry level?
- It is marked Medium. Entry-level engineers can practise it, but it expects you to reason about requirements and trade-offs, not only list components.
- What should I cover first?
- Start with the product goal, how success is measured and what data is available. Agree on scope with the interviewer before you design anything.
- Can I practise it for free?
- It is a premium question. Sign up and unlock it once for 10 credits; it then stays unlocked. When you finish, Lala, your personalized AI mentor, can review your design for 30 credits.
Related questions
Updated · Written by the SevyDevy team