Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how to build real-time analytics systems for sports betting applications using Spark Structured Streaming in this 35-minute conference talk from Databricks. Discover how DraftKings tackles the challenges of sports trading, where precision and adaptability are crucial for managing risk and preventing model miscalculations that could lead to significant losses. Explore the complexities of real-time pricing for hundreds of interdependent markets while maintaining accurate correlations and incorporating trader inputs like player skill-level adjustments. Understand why black-box models are insufficient in this domain and how constant feedback loops drive informed decision-making. See how DraftKings exposes real-time metrics from their simulation engine to provide traders with deeper insights into how their inputs influence model behavior. Master the technical implementation using Spark Structured Streaming, Kafka, and Databricks dashboards to transform raw simulation outputs into actionable data. Gain insights into how this transparency enables fine-grained control over pricing, resulting in more accurate odds, improved sportsbook efficiency, and enhanced customer experiences. The presentation is delivered by Aaron Hope, Lead Machine Learning Engineer, and Ethan Summers, Lead Data Science Engineer, both from DraftKings, sharing real-world expertise from production sports betting systems.
