Football is complex, but your code doesn’t have to be — meet DataBallPy and a practical deep dive into pressing
summary
DataBallPy is an open‑source Python package that actually gives a usable pipeline: a synchronization algorithm reduces timestamp error from ~4s to within one frame, adapters for Kloppy/Opta/StatsBomb, and built‑in metrics so analysis starts in minutes. The RBFA case uses those tools on 226 matches, 16,121 pressing instances and finds successful presses cover less distance but show more accelerations, effects largest at high block and negligible between‑team variance. The team ships a Pressure Pack dashboard that visualizes results and is already used in practice.
AI-written summary · about
chapters (21)
- 0:00Welcome
- 0:25Datable pie for soccer analytics
- 1:49Event and tracking data sources
- 2:52Synchronizing tracking and event data
- 5:23Solving synchronization with datable pie
- 6:48Loading datable pie game objects
- 8:34Synchronizing data in practice
- 9:15Key features of datable pie
- 10:21Computing metrics with datable pie
- 11:44Visualizing soccer data with datable pie
- 12:47Tiko pressing analysis at RBFA
- 13:29Defining efficient pressing
- 14:55Datable pie for pressing analysis
- 16:01Pressure intensity model and intercept time
- 18:07Defining pressing instances
- 19:31Analyzing 226 matches for pressing
- 21:17Pressing performance context
- 22:43Key findings on pressing
- 24:28Introducing pressure pack dashboard
- 25:52Exploring pressure pack features
- 26:38Q&A
related talks
41mFootball's data analytics in python
41mThe evolution of basketball with data science
51mVideo Analytics for Football games
32mCutting Edge Football Analytics in Python
23mSport analysis with Python
38mDeep Learning plays Handball
33mUsing Data Science to Better Evaluate American Football Players
35mFootball video analysis using Deep Learning