databricks Databricks Blog ·

Databricks Coach's Corner: Soccer App Leverages Full Platform

blogdataaidatabricksengineer
feature announcement

Databricks has launched Coach's Corner, a soccer coaching application that transforms 51 million rows of match data into a real-time 2D/3D tactical analysis tool. This end-to-end solution showcases the Databricks platform's capabilities from data ingestion via Lakeflow to AI scouting with Genie and Vector Search, all governed by Unity Catalog. The app is designed for coaches to make split-second decisions by providing low-latency data access for replays and optimized query paths for complex analytics, demonstrating a unified approach to data and AI on the platform.

  • Coach's Corner tactical analysis application launched
  • End-to-end platform integration from ingestion to AI
  • Optimized data serving paths for speed and scale
  • Unified governance and lineage with Unity Catalog
  • Advanced data quality enforcement with Spark Declarative Pipelines
Features (1)
  • Coach's Corner tactical analysis application launched

    Coach's Corner is a Databricks App that transforms 25 fps match tracking data into a sub-second 2D/3D tactical bench with replays, event analytics, a scout chat, and an opponent-dossier agent.

Enhancements (4)
  • End-to-end platform integration from ingestion to AI

    The application utilizes Databricks' Lakeflow for data ingestion, DBSQL for querying, and Lakebase for serving data, with an AI layer powered by a Genie space, Vector Search, and an LLM through the Unity AI Gateway, all traced in MLflow.

  • Optimized data serving paths for speed and scale

    High-speed tracking replays are powered by Lakebase synchronizing gold tables to Postgres for millisecond-level reads, while heavy event analytics use the Statement Execution API to DBSQL for optimized computational queries.

  • Unified governance and lineage with Unity Catalog

    Consolidating volumes, tables, models, and indexes into a single Unity Catalog eliminates vendor glue code and secondary governance systems, ensuring consistent data and model lineage across the platform.

  • Advanced data quality enforcement with Spark Declarative Pipelines

    Spark Declarative Pipelines process data through bronze, silver, and gold tiers, enforcing 46 data quality expectations to safeguard the pipeline and establish data correctness for downstream consumers.

Notes (1)
  • Application design prioritizes coach's natural instinct

    The user interface is designed to reduce interaction overhead, favor spatial context over traditional graphing, and present metrics as dynamic elements of the game, eliminating the need for manual data interpretation.

Read the original announcement →

https://www.databricks.com/blog/building-soccer-coaching-app-databricks

Related releases