Riot Games
Customer Case Study
Riot Games’ goal is to be the world’s most player-focused gaming company in the world. Founded in 2006, and based in LA, Riot Games is best known for the League of Legends game. Over 100 million gamers play every month.
Vertical Use Case
Improving gaming experience through:
• Network performance monitoring
• Combating in-game abusive language
Technical Use Case
• Data Ingest and ETL
• Streaming
• Machine Learning
• Deep Learning
The Challenges
- Content Recommendations: Need to build ML models that are capable of providing personalized in-game offers to 67M+ monthly gamers.
- Gaming Lag: Manually monitoring petabytes of streaming network data across 200,000+ city and ISP configurations is near impossible, making it hard to proactively pinpoint network issues that adversely impact gaming experiences.
- Disjointed Infrastructure: Moving data across disjointed systems and data analytics tools hinders team agility and collaboration.
The Solution
When it came time to choose a new solution to power their in-game insights, Riot Games selected Databricks for its ability to provide a production-ready Apache SparkTM platform that fully met the needs of both data science and engineering.
- Unified Analytics Platform: Streamlines analytics workflows across cross-functional teams with a single platform for querying, debugging and exploring streaming and batch data as well as building and deploying ML models.
- Interactive Workspaces: Fosters collaboration with a shared notebook environment that enables data scientists to rapidly iterate on models in real-time.
- Simplified Management: Able to fully automate job scheduling, monitoring, and cluster management without human intervention.
The Results
Databricks allows Riot Games to improve the gaming experience of their players by providing scalable, fast analytics:
- Improved In-Game Purchase Experience: Able to rapidly build and productionize recommendation engine that provides unique offers based on over 500B data points. Gamers can now more easily find the content they want.
- Reduced Game Lag: Built ML model that detects network issues in real-time, enabling Riot Games to avoid outages before they adversely impact players.
- Faster Analytics: Increased processing performance of data preparation and exploration, significantly speeding up analysis.
We wanted to free data scientists from managing clusters. Having an easy-to-use, managed Spark solution in Databricks allows us to do this. Now our teams can focus on improving the gaming experience.