SciSports: Learning football kinematics through two-dimensional tracking data Anatoliy Babic, Harshit Bansal, Gianluca Finocchio, Julian Golak, Mark Peletier, Jim Portegies, Clara Stegehuis, Anuj Tyagi, Roland Vincze, William Weimin Yoo August 15, 2018 Abstract SciSports is a Dutch startup company specializing in football analytics. This paper describes a joint research effort with SciSports, during the Study Group Mathematics with Industry 2018 at Eindhoven, the Netherlands. The main challenge that we addressed was to automatically process empirical football players' trajectories, in order to extract useful information from them. The data provided to us was two-dimensional positional data during entire matches. We developed methods based on Newtonian mechanics and the Kalman filter, Generative Adversarial Nets and Variational Autoencoders. In addition, we trained a discriminator network to recognize and discern different movement patterns of players. The Kalman-filter approach yields an interpretable model, in which a small number of player-dependent parameters can be fit; in theory this could be used to distinguish among players. The Generative-Adversarial-Nets approach appears promising in theory, and some initial tests showed an improvement with respect to the baseline, but the limits in time and computational power meant that we could not fully explore it. We also trained a Discriminator network to distinguish between two players based on their trajectories; after training, the network managed to distinguish between some pairs of players, but not between others. After training, the Variational Autoencoders generated trajectories that are difficult to distinguish, visually, from the data. These experiments provide an indication that deep generative models can learn the underlying structure and statistics of football players' trajectories. This can serve as a starting point for determining player qualities based on such trajectory data. Keywords: Football, Trajectory, Newtonian mechanics, Kalman filter, Machine Learning, Generative Adversarial Nets, Variational Autoencoder, Discriminator 1 Introduction SciSports (http://www.scisports.com/) is a Dutch sports analytics company taking a data-driven approach to football. The company conducts scouting activities for football clubs, gives advice to football players about which football club might suit them best, and quantifies the abilities of football players through various performance metrics.

Netherlands-based data intelligence company SciSports is hoping to change world football through data, motion tracking and machine learning. Using data and machine learning, the company produces a "SciSkill Index" – an objective ranking of current ability, potential and influence of thousands of footballers across hundreds of different competitions around the world. The score is determined by the SciSports' existing data library and from 3D data collected from stadium cameras, which converts movements in practice or during the match into useful information in real time. "It is the first system that allows you to compare James Troisi with Neymar and check if Milos Degenek has the potential to become as good as David Luiz," a company spokesperson told Which-50. "This will enable clubs to increase their scouting scope, decrease their risk of signing the wrong player and enlarge the change of finding the right talent."

Netherlands-based data intelligence company SciSports is hoping to change world football through data, motion tracking and machine learning. Using data and machine learning, the company produces a "SciSkill Index" – an objective ranking of current ability, potential and influence of thousands of footballers across hundreds of different competitions around the world. The score is determined by the SciSports' existing data library and from 3D data collected from stadium cameras, which converts movements in practice or during the match into useful information in real time. "It is the first system that allows you to compare James Troisi with Neymar and check if Milos Degenek has the potential to become as good as David Luiz," a company spokesperson told Which-50. "This will enable clubs to increase their scouting scope, decrease their risk of signing the wrong player and enlarge the change of finding the right talent."

Analytics leader SAS is helping customers gain more value from data with SAS Viya products, extending the value from the SAS Platform. These newest advances, such as embedded artificial intelligence (AI) capabilities, will further address the needs of organisations that are making analytics core to their business. A variety of industries, countries and organisation sizes have embraced SAS Viya products. With SAS, data scientists, analysts, developers, IT, domain experts and executives can all generate data-driven insights – from the same, consistent data, fostering greater collaboration and driving innovations faster. SAS continues to deliver new capabilities, such as image recognition, deep learning and natural language understanding into the SAS Platform. With football (that's soccer in the U.S) contracts being signed at upwards of 50 million US dollars, it is important that agents and clubs understand as much about a player as possible.