Title: Positional value in soccer: Expected league points added above replacement
Authors: Konstantinos Pelechrinis - University of Pittsburgh (United States)
Wayne Winston - Indiana University (United States)
Xin Liu - School of Computing and Information, University of Pittsburgh (United States) [presenting]
Abstract: Soccer is undeniably the most popular sport world-wide, but at the same time it is one of the least quantified. While there are many reasons for this, one of the main is the difficulty to explicitly quantify the contribution of every player on the field to his team chances of winning. For example, successful advanced metrics such as the (adjusted) +/- that allows for division of credit among a basketball team's players (and ultimately to obtain a view of the wins contributed by a player), fail to work in soccer due to severe co-linearities (i.e., the same players being on the field for the majority of the time). We take a first step towards developing metrics that can estimate the contribution of a soccer player to his team's winning chances. In particular, using data from (i) approximately 20,000 games from 11 European leagues for 8 seasons, as well as, (ii) player ratings from FIFA, we estimate through a Skellam regression model the importance of every line in winning a soccer game. We consequently translate the model to expected league points added (per game) above a replacement player method. This model can be used as a guide for contracts' monetary value decisions. For example, using market value data for approximately 10,000 players we further identify that currently the market clearly under-values defensive line players relative to goalkeepers. Finally, we discuss how this model can be significantly enhanced using optical tracking data.