Streaming the Game: Scaling Real-Time Intelligence at DraftKings With Kafka, Databricks & Sigma

DraftKings set out to build a real-time analytics capability before the use cases were fully defined. Rather than waiting for perfect requirements, we invested in the streaming foundation first — allowing meaningful use cases to emerge from the platform itself.We assembled an initial solution to deliver second-level visibility into transactions, active users, and revenue. As stakeholders gained live insight, new needs surfaced — including real-time liability tracking and deeper financial monitoring — many not originally envisioned.

As adoption expanded, we evolved the architecture to Kafka, Databricks Spark Declarative Pipelines and Real-Time Mode, as well as Sigma to improve scalability, flexibility, and governance. In this session, we will review the architectural evolution, key streaming design decisions, and how we blend real-time, historical, and forecast data into a financial intelligence system.Attendees will leave with practical lessons for designing streaming-first systems when requirements are evolving.