Time Series Modeling for Dream Team in Fantasy Premier League

The performance of football players in English Premier League varies largely from season to season and for different teams. It is evident that a method capable of forecasting and analyzing the future of these players on-field antics shall assist the management to a great extent. In a simulated environment like the Fantasy Premier League, enthusiasts from all over the world participate and manage the players catalogue for the entire season. Due to the dynamic nature of points system, there is no known approach for the formulation of a dream team. This study aims to tackle this problem by using a hybrid of Autoregressive Integrated Moving Average (ARIMA) and Recurrent Neural Networks (RNNs) for time series prediction of player points and subsequent maximization of total points using Linear Programming (LPP). Given the player points for the past three seasons, the predictions have been made for the current season by modeling differently for ARIMA and RNN, and then creating an ensemble of the same. Prior to that, proper data preprocessing techniques were deployed to enhance the efficacy of the prepared model. Constraints on the type of players like goalkeepers, defenders, midfielders and forwards along with the total budget were effectively optimized using LPP approach. The validation of the proposed team was done with the performance in upcoming season, where the players outperform as expected, and helped in strengthening the feasibility of the solution. Likewise, the proposed approach can be extended to English Premier League by official managers on-field.

[1]  Jahangir Soleimani-Damaneh,et al.  Evaluating the Performance of Iranian Football Teams Utilizing Linear Programming , 2011 .

[2]  Dino Pedreschi,et al.  The harsh rule of the goals: Data-driven performance indicators for football teams , 2015, 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[3]  Hung Man Tong,et al.  Threshold models in non-linear time series analysis. Lecture notes in statistics, No.21 , 1983 .

[4]  M. Lewis,et al.  Moneyball: The Art of Winning an Unfair Game , 2003 .

[5]  J. Gooijer,et al.  Some recent developments in non-linear time series modelling, testing, and forecasting☆ , 1992 .

[6]  C. Granger,et al.  An introduction to bilinear time series models , 1979 .

[7]  Craig Wright,et al.  The wider context of performance analysis and it application in the football coaching process , 2014 .

[8]  P. Krustrup,et al.  High-intensity running in English FA Premier League soccer matches , 2009, Journal of sports sciences.

[9]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[10]  Stephen Morrow,et al.  Measuring efficiency and productivity in professional football teams: evidence from the English Premier League , 2007, Central Eur. J. Oper. Res..

[11]  Matthew Weston,et al.  Analysis of physical match performance in English Premier League soccer referees with particular reference to first half and player work rates. , 2007, Journal of science and medicine in sport.

[12]  Carlo Castagna,et al.  Ageing and physical match performance in English Premier League soccer referees. , 2010, Journal of science and medicine in sport.

[13]  Christopher A Barnes,et al.  Factors associated with increased propensity for hamstring injury in English Premier League soccer players. , 2010, Journal of science and medicine in sport.

[14]  R. Engle Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[15]  Luca Pappalardo,et al.  A network-based approach to evaluate the performance of football teams , 2015 .

[16]  Arend Hintze,et al.  Data Preprocessing , 2017, Encyclopedia of Machine Learning and Data Mining.