Sports analytics is on the rise across sports and markets. In basketball, the NBA is leading the innovation in this space, whereas European basketball is lagging behind, with fewer tools and less data. In this talk, I will introduce an open-source Python library designed to extract and analyze Euroleague (European) basketball data. I will highlight the types of data available and demonstrate its versatility through real-world use cases for generating player and team insights. I will present a knowledge graph on basketball data and show how it brings a new dimension into insights extraction for teams and players. Finally, I will showcase a simulation framework that uses this data to model league games and project team performances throughout the season using their Elo rating and defensive and offensive ratings.
Technical level: Introductory level/students (some technical knowledge needed)
Session Length: 40 minutes
Supported by
