The effects of scheduling network models in predictive processes in sports

Abstract

In many sports disciplines, the schedule of the competitions is undeniably an inherent yet crucial component. The present study modeled sports competitions schedules as networks and investigated the influence of network properties on the accuracy of predictive ratings and forecasting models in sports. Artificial networks were generated representing competition schedules with varying density, degree distribution and modularity and embedded in a full rating and forecasting process using ELO ratings and an ordered logistic regression model. Results showed that network properties should be considered when tuning predictive ratings and revealed several aspects for improvement. High density does not increase rating accuracy, so improved rating approaches should increasingly use indirect comparisons to profit from transitivity in dense networks. In networks with a high disparity in their degree distribution, inaccuracies are mainly driven by nodes with a low degree, which could be improved by relaxing the rating adjustment functions. Moreover, in terms of modularity, low connectivity between groups (i.e., leagues or divisions) challenges correctly assessing a single group’s overall rating. The present study aims to stimulate discussion on network properties as a neglected facet of sports forecasting and artificial data to improve predictive ratings.