Predicting Soccer Events from Optical Tracking Data

2018-01-01
Ozdemir, Esref
Alemdar, Hande
In this study, an automated method for predicting soccer events such as corner kick, free kick, goals and penalties has been developed using optical tracking data with random forest classifier. The study was conducted on a dataset of 140 matches from Turkish Football Federation Super League 2017-2018 season. The average accuracy on validation set is %93.8 and %91.4 on a separate held-out test set.
26th IEEE Signal Processing and Communications Applications Conference (SIU)
Citation Formats
E. Ozdemir and H. Alemdar, “Predicting Soccer Events from Optical Tracking Data,” presented at the 26th IEEE Signal Processing and Communications Applications Conference (SIU), İzmir, Türkiye, 2018, Accessed: 00, 2025. [Online]. Available: https://hdl.handle.net/11511/118138.