Title: Predictive power of fantasy sports data for soccer forecasting

Authors: Erik Štrumbelj; Marko Robnik-Šikonja

Addresses: University of Ljubljana, Faculty of Computer and Information Science, Tržaška 25, 1001 Ljubljana, Slovenia ' University of Ljubljana, Faculty of Computer and Information Science, Tržaška 25, 1001 Ljubljana, Slovenia

Abstract: We analyse data from 5,000 competitors who participated in an online soccer managerial game which revolved around the English Premier League (EPL). We show that competitors incorporate into their decisions relevant information about the outcome of a soccer match. Furthermore, forecasts based on managerial game data are significantly better than random forecasts, forecasts based on relative frequency, and forecasts based on teams' attendance, but worse than bookmaker odds. Our work provides an evidence that crowds poses significant amount of information for the match outcome prediction.

Keywords: data analytics; fantasy sport games; result forecasting; fantasy football; football results; soccer results; English Premier League; EPL; Fantasy Premier League; match outcome prediction; football matches; soccer matches; random forecasts; relative frequency; team attendances; bookmaker odds.

DOI: 10.1504/IJDMMM.2015.069247

International Journal of Data Mining, Modelling and Management, 2015 Vol.7 No.2, pp.154 - 163

Published online: 06 May 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article