Data Science in Gaming
summary
Gameloft describes concrete systems for monetization and measurement: an in‑game IP shop with targeted offers, dynamic pricing tradeoffs, and subscription/battle‑pass experiments that raise both revenue and engagement. The team builds an AB testing framework but often uses causal impact analysis and mix models when A/B is impossible; a sustained 1–5% uplift is treated as actionable. A churn model flags inactivity and crash counts — the latter shows a surprising negative correlation with churn — and privacy rules force opt‑in personalization and clearer player choices.
AI-written summary · about
chapters (11)
- 0:00Data science in gaming
- 4:55GameLoft’s data science team
- 9:55Data science applications in gaming
- 15:15Monetization in free-to-play
- 22:24Dynamic pricing and ethical AI
- 28:27Advertising optimization
- 32:23Battle pass and subscriptions
- 35:35A/B testing for game design
- 37:47Causal inference in marketing
- 43:54Predicting player churn
- 47:30Key takeaways
related talks
30mOptimizing Mobile Game LiveOps with Data-Driven Decisions
17mBuilding a Long-term Gaming App Business: Applying Lessons of the Past to Power Your Success
40mDesigning games for optimal IAP
45mDesigning games for maximum monetisation
37mHypercasual monetisation versus long-term retention monetisation
34mData Science Challenges in the Mobile Games Industry
49mMonetisation Design - A Story of Love and Retention
19mData-driven optimisation for in-app purchases and gameplay