Football Analytics with the Soccermatics Package
summary
Football analytics package that standardizes disparate event data (StatsBomb World Cup 2018, FA WSL, NWSL) into consistent pitch coordinates using soccer_transform and plots with soccer_pitch and shot/XG helpers. It builds heat maps, pass networks, per-player contributions and an XG timeline, handles differing field schemas and produces Monte Carlo score simulations. Current workflow auto-checks updates via Gmail; goal is real-time deployment and ggplot extension support. Claim: four billion fans matter, but usable analytics come from data cleaning, XG models and usable plotting tools.
AI-written summary · about
chapters (15)
- 0:00Introduction to Soccermatics
- 1:06Football analytics lag behind other sports
- 2:29Event data and tracking technology
- 4:55Open data initiatives in football
- 5:57Soccermatics package overview
- 7:01Visualizing data on a pitch
- 8:05Heat maps and player positions
- 9:30Pass networks and team interactions
- 10:14Expected goals explained
- 11:41Analyzing shots with xG
- 12:22Expected goals timeline
- 13:04Real-world applications of Soccermatics
- 14:46Automating analytics workflows
- 15:52Future directions for the package
- 17:35Monte Carlo simulations and tracking data
related talks
29mFootball (soccer) data analysis: A pedagogic introduction
41mFootball's data analytics in python
11mIntroduction to Soccer Pass Network Analysis with Python
56mSports Analytics: Big Data in the Big Time
32mCutting Edge Football Analytics in Python
45mThe Technical Journey to Define the True Value of a Football Goal
04mInteractive Sports Analytics
41mThe evolution of basketball with data science