← stubhub Interview Insights

stubhub·Software Engineer·Onsite - System Design / Architecture·Senior

Senior
Apr 2026

Summary

StubHub system design round focused on a MarketingEngine I'd supposedly already built, then pivoted into an open-ended discussion about how to make the recommendation logic smarter. The open discussion portion was way more involved than I expected.

Questions Asked (1)

Q1

You've built a MarketingEngine with rule-based event notification campaigns. How would you improve the recommendation logic beyond simple rules like city matching, birthday proximity, and nearest events?

Product Sense & IdeationSystem DesignA/B Testing & Experimentation
Author's notes

This is the kind of question where you can ramble forever and still feel like you said nothing useful.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by acknowledging the limitations of rule-based systems, then propose a hybrid approach that combines collaborative filtering, content-based filtering, and contextual bandits. Emphasize the importance of defining clear business metrics and setting up A/B tests to validate improvements. Finally, discuss how to handle cold-start and scalability challenges.

Pro tip: Frame your answer around measurable business impact—tie each improvement to metrics like click-through rate, conversion, or retention, and mention how you'd validate with A/B tests. This shows you think like a product-minded engineer.

1. Identify limitations of current rules

Explain that rule-based systems are static, don't personalize beyond simple attributes, and can't adapt to user behavior over time. This sets the stage for why improvements are needed.

2. Propose a hybrid recommendation approach

Combine collaborative filtering (user-user or item-item) to capture latent preferences, content-based filtering to use event attributes, and contextual bandits to balance exploration and exploitation.

3. Incorporate real-time and contextual signals

Use session data, location, time, device, and past interactions to dynamically adjust recommendations. Mention feature stores and online learning for low-latency updates.

4. Define evaluation metrics and experimentation plan

Choose offline metrics (precision@k, recall, NDCG) and online metrics (CTR, conversion, revenue). Design A/B tests with proper control and treatment groups, and consider multi-armed bandit for continuous optimization.

5. Address cold-start and scalability

Discuss fallback strategies for new users/events (e.g., popularity, content similarity) and system design for scale (e.g., precomputed recommendations, caching, distributed processing).

Key Points to Mention

  • Collaborative filtering (matrix factorization, neural networks) for personalization
  • Contextual bandits for exploration-exploitation trade-off
  • Feature engineering with user and event attributes
  • Offline evaluation metrics (precision, recall, NDCG) and online A/B testing
  • Cold-start problem and fallback strategies
  • Scalability considerations (real-time serving, distributed training)

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