The document discusses using predictive analytics and machine learning to improve gaming analytics. It outlines six potential use cases: 1) predicting new player churn, 2) predicting veteran player churn, 3) survival analysis of player populations, 4) gameplay analysis to identify issues, 5) fraud detection, and 6) identifying high-spending "whale" players early. The presentation emphasizes the importance of collecting extensive player data, using techniques like supervised and unsupervised learning to build predictive models, and taking action based on predictions to improve the player experience and business metrics.
31. Data Collection in
Cloud
Game
Mess
Bus
Summarization
Large Scale
Storage
• Game is fully instrumented
• Messages sent to server via
message bus architecture (in
background and batched)
Data
Ingestion
• Standard “NoSQL” stack (storage
with Hadoop/Pig layered on top)
• Streaming event aggregation often
done by aggregating into in-
memory caching (memcached or
elasticcache).
• Often the large-scale storage is
simply json files stored in S3
• Large scale storage can run into
tens of gigabytes a day. Can be
significant cost over time
• What we know and
love
Example Architecture