Improving Event Data in Football Matches: A Case Study Model for Synchronizing Passing Events with Positional Data

Abstract

In football, accurately pinpointing key events like passes is vital for analyzing player and team performance. Despite continuous technological advancements, existing tracking systems still face challenges in accurately synchronizing events and positional data accurately. This is a case study that proposes a new method to synchronize events and positional data collected during football matches. Three datasets were used to perform this study: a dataset created by applying a custom algorithm that synchronizes positional and event data, referred to as the optimized synchronization dataset (OSD); a simple temporal alignment between positional and event data, referred to as the raw synchronization dataset (RSD); and a manual notational data (MND) from the match video footage, considered the ground truth observations. The timestamp of the pass in both synchronized datasets was compared to the ground truth observations (MND). Spatial differences in OSD were also compared to the RSD data and to the original data from the provider. Root mean square error (RMSE) and mean absolute error (MAE) were utilized to assess the accuracy of both procedures. More accurate results were observed for optimized dataset, with RMSE values of RSD = 75.16 ms (milliseconds) and OSD = 72.7 ms, and MAE values RSD = 60.50 ms and OSD = 59.73 ms. Spatial accuracy also improved, with OSD showing reduced deviation from RSD compared to the original event data. The mean positional deviation was reduced from 1.59 ± 0.82 m in original event data to 0.41 ± 0.75 m in RSD. In conclusion, the model offers a more accurate method for synchronizing independent datasets for event and positional data. This is particularly beneficial for applications where precise timing and spatial location of actions are critical. In contrast to previous synchronization methods, this approach simplifies the process by using an automated technique based on patterns of ball velocity. This streamlines synchronization across datasets, reduces the need for manual intervention, and makes the method more practical for routine use in applied settings.