← StubHub Interview Insights

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

SeniorPrefer not to say
Apr 2026

Summary

StubHub system design round focused on a MarketingEngine for event notifications. The open-ended discussion about improving recommendation logic beyond basic rules was the whole thing, no coding, just a long back-and-forth about ML and ranking systems.

Questions Asked (1)

Q1

You've built a MarketingEngine that sends rule-based event notifications to customers (notify when an event is in their city, closest to their birthday, or the 5 geographically nearest). How would you improve the recommendation logic beyond these simple rules?

System DesignProduct Sense & IdeationA/B Testing & Experimentation
Author's notes

This question sprawled in ways I wasn't fully ready for.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by acknowledging the current rule-based system and its limitations, then propose a hybrid approach that combines collaborative filtering, content-based filtering, and contextual signals. Emphasize the importance of experimentation and metrics to validate improvements, and discuss how to handle cold-start and scalability.

Pro tip: Frame your answer around business impact: tie each recommendation improvement to metrics like conversion rate, customer engagement, and retention. Also, mention how you would A/B test these changes to measure incremental lift.

1. Identify limitations of current rules

Discuss how simple rules may lead to suboptimal recommendations due to lack of personalization, inability to capture complex preferences, and failure to adapt to changing user behavior.

2. Incorporate user behavior and preferences

Propose using collaborative filtering (user-based or item-based) and content-based filtering to leverage historical data such as past purchases, views, and searches to generate personalized recommendations.

3. Add contextual and real-time signals

Suggest incorporating contextual factors like time of day, device, location, and real-time event popularity to make recommendations more relevant and timely.

4. Design a hybrid recommendation system

Explain how to combine multiple approaches (e.g., weighted hybrid, switching hybrid) to balance personalization with business rules and handle cold-start users/events.

5. Implement experimentation and feedback loops

Outline an A/B testing framework to compare new algorithms against the baseline, measure key metrics (CTR, conversion, retention), and continuously refine the model based on user feedback.

Key Points to Mention

  • Collaborative filtering (user-based and item-based) to find similar users/events
  • Content-based filtering using event attributes (genre, artist, venue) and user profiles
  • Contextual bandits or reinforcement learning for real-time personalization
  • Handling cold-start with fallback rules or demographic-based recommendations
  • A/B testing methodology: hypothesis, metrics, sample size, and statistical significance
  • Scalability considerations: distributed computing, caching, and model serving

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