Riot Games — Teamfight Tactics — A/B Test & Causal Inference Questions

Role context: Insights Analyst, AXE — Teamfight Tactics · Est. study time: 70 min · 7 questions

Experimentation in F2P monetization

This section focuses on the experiment-design and causal-inference questions a monetization analyst is tested on — sizing and reading a test, variance reduction, and the price/event decisions you can't cleanly A/B test. (For the probability and statistics fundamentals — p-values, error types, distributions — see the Probability & Statistics section.) Testing on a cosmetics-only, live-service game is hard for reasons specific to monetization, and the questions lean here:

• Revenue is heavy-tailed. A few whales dominate, so revenue means are noisy and outlier-driven — variance, not bias, is the enemy. This shapes sizing, test choice, and analysis (capping, CUPED, payer-rate vs ARPPU split).
• You usually can't A/B a price per player. Fairness forbids charging different players different prices, so price questions become price-elasticity modeling and regional/time quasi-experiments.
• Events resist clean A/B tests. One-shot, time-boxed, and novel — "it spiked" can be a pull-forward, not incremental revenue.
• LTV is delayed and censored, so you read tests on validated surrogate metrics.

The unit of randomization is the account (one identity across PC + mobile). Each answer is a coaching walkthrough: a Sample answer (clarify the setup → lay out the approach → a simulated back-and-forth with the interviewer → a clear call), then a Deep dive with illustrative example carrying the real math and charts, then a Grading rubric.