TY - JOUR

T1 - Predicting the future performance of soccer players

AU - Arndt, Cornelius

AU - Brefeld, Ulf

PY - 2016/10/1

Y1 - 2016/10/1

N2 - We propose a multitask, regression-based approach for predicting future performances of soccer players. The multitask approach allows us to simultaneously learn individual player models as offsets to a general model. We devise multitask variants of ridge regression and ε-support vector regression. Together with a hashed joint feature space, the generalized models can be optimized using standard techniques. Relevant features for the prediction are identified by a modified recursive feature elimination strategy. We report on extensive empirical results using real data from the German Bundesliga.

AB - We propose a multitask, regression-based approach for predicting future performances of soccer players. The multitask approach allows us to simultaneously learn individual player models as offsets to a general model. We devise multitask variants of ridge regression and ε-support vector regression. Together with a hashed joint feature space, the generalized models can be optimized using standard techniques. Relevant features for the prediction are identified by a modified recursive feature elimination strategy. We report on extensive empirical results using real data from the German Bundesliga.

KW - feature selection

KW - machine learning

KW - multitask regression

KW - predictive analytics

KW - ridge regression

KW - support vector regression

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=84988431971&partnerID=8YFLogxK

U2 - 10.1002/sam.11321

DO - 10.1002/sam.11321

M3 - Journal articles

AN - SCOPUS:84988431971

VL - 9

SP - 373

EP - 382

JO - Statistical Analysis and Data Mining

JF - Statistical Analysis and Data Mining

SN - 1932-1864

IS - 5

ER -