How to Enhance the Gaming Experience Through Content Micro-personalisation
summary
JUMP deploys a cloud data pipeline that ingests game telemetry into a data lake, runs AI models for disengagement prediction and per-player purchase recommendations, and delivers results via SDK+API delivery. Models mix machine learning with business rules, use catalog metadata and player clustering when per-user recommendations aren’t feasible, and require A/B experiment design to separate model accuracy from campaign effects. A live integration with Digital Legends’ Respawnables produces measurable uplifts in transactions and revenue.
AI-written summary · about
chapters (16)
- 0:00Introduction
- 1:37Presentation
- 4:08Context
- 5:02Challenges
- 7:16Jump
- 8:41Clients
- 10:12How to get your data
- 11:53Player Profiling
- 17:40disengagement model
- 18:13personalizer
- 24:27catalog
- 29:53KPIs
- 31:11Recommendations
- 32:13Impact of Actions
- 33:36Digital Legends Example
- 34:56Outro
related talks
23mCustom-made games with machine learning and big data
20mUsers acquired - Now what?: Maximising revenue from existing players
27mEnhancing Personalization Using Recommendation Systems & Multi-Armed Bandits
19mMachine Learning is a new age of Personalized Game Monetization
58mUnleashing the Power of AI to Personalize Games
29mHow to Build a Player-centric Business Model (That's Resilient Enough for the Next Decade)
01h 00mHow to win at monetizing games as a service
24mEngaging new and diverse audiences with ML