TY - JOUR AU - Kontos, Christos AU - Karlis, Dimitris PY - 2023/05/23 Y2 - 2024/03/29 TI - Football analytics based on player tracking data using interpolation techniques for the prediction of missing coordinates JF - Statistica Applicata - Italian Journal of Applied Statistics JA - sa-ijas VL - 35 IS - 2 SE - Latest articles DO - 10.26398/IJAS.0035-010 UR - https://www.sa-ijas.org/ojs/index.php/sa-ijas/article/view/202 SP - AB - <p class="abstract"><span lang="EN-US">In recent days we have seen an increasing interest in using tracking data for sports and especially for football. Such data can reveal the location of the players and the ball many times per second allowing for examining tactics, efficiency of players, formations, and many others characteristics of the game. Unfortunately, such systems are still expensive, and their data are not widely available. As an alternative, limited tracking data can be obtained from broadcasting videos. They are of less quality and of course the are censored in the sense that they do not provide information for all players but only those in the frame taken. Within this framework, the primary aim of this paper, is the exploration of the most suitable method for retrieving the missing information of players’ and ball’s positions and rectify as much as possible the effect of censoring which leads to discontinuous player tracks and unreliable player identification. In this paper we explored and compared different interpolation methodologies. Moreover, we tried to distinguish possible differences between the actual data, as they were tracked from the camera and the interpolated data that have been estimated from our best selected method, by extracting insights that are mainly based on tactical analyses as well as on players’ performances.</span></p> ER -