Google·Product Manager·Onsite - Product Sense / Strategy·Senior

SeniorPrefer not to say

Jun 2026

Summary

Google product sense interview, just one question about music recommendations on Spotify. Short session, not much to go on, but the question itself had some depth to it.

Questions Asked (1)

How would you design a feature to recommend similar artists on Spotify?

Product Sense & IdeationProduct StrategySystem Design

Author's notes

I went straight into user segmentation and kind of forgot to anchor on what problem we were actually solving.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the goal and constraints, then structure your answer around user needs, data signals, and algorithmic approaches. Propose a concrete design with trade-offs, and define success metrics and potential risks.

Pro tip: Emphasize how you would balance exploration and exploitation to avoid popularity bias, and discuss how to evaluate the feature with A/B tests measuring both engagement and discovery.

1. Clarify Objective and Scope

Ask clarifying questions to understand the goal (e.g., increase engagement, discovery) and constraints (e.g., data availability, latency). Define what 'similar' means in terms of musical attributes, user behavior, or both.

2. Identify Data Signals

List relevant data sources: user listening history, playlists, skips, likes, audio features (tempo, key), artist metadata, and social signals. Consider both implicit and explicit feedback.

3. Choose Algorithmic Approach

Propose methods like collaborative filtering (user-based or item-based), content-based filtering using audio features, or hybrid models. Discuss how to handle cold start and scalability.

4. Design User Experience

Describe where and how recommendations appear (e.g., artist page, radio, home). Ensure explanations are clear (e.g., 'Because you listened to X') and allow user feedback.

5. Define Metrics and Evaluate

Specify success metrics (e.g., click-through rate, listening time, discovery rate) and how to measure them via A/B tests. Address potential biases and long-term impact.

Key Points to Mention

Collaborative filtering vs. content-based filtering and hybrid approaches
Handling cold start for new artists and users
Balancing popularity bias with niche recommendations
Using audio features (e.g., tempo, energy) for similarity
A/B testing and defining success metrics like engagement and discovery
Scalability and real-time vs. batch processing

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.