Research on winning rate prediction of e-sport League of Legends based on machine learning

E-sport project League of Legends is a top event with a complex mechanism, in order to improve accuracy win rate prediction of League of Legends, the logarithmic energy entropy generates expansion vectors as grouping strategy to enhance contextual information between use of heroes with stronger relationship features, using regulating force mechanism to assign heroes feature weights, extracts heroes lineup selection and role relationship position signal features in turn, establishes a win rate prediction model to combine convolution neural network as a classifier to fully extract the deeper features. Simulation results show that the proposed grouping strategy and feature combination strategy can obtain an overall prediction accuracy 75.32%, which can effectively improve the prediction model accuracy.