Competition result prediction method, device and equipment based on machine learning

Abstract

The invention relates to a competition result prediction method, device and system based on machine learning. The competition result prediction method comprises: determining competition participationobjects of a target competition; determining feature data of the participating objects based on the historical competition data of the participating objects; obtaining competition result interferencedata of the participating objects; performing competition result prediction on the characteristic data and the competition result interference data based on a first competition result prediction modelto obtain first competition result data of the target competition, and learning the characteristic data and the competition result interference data of the participating objects through the competition result prediction model to improve the accuracy of competition result prediction.

Description

technical field [0001] The present disclosure relates to the technical field of machine learning, in particular to a method, device and equipment for predicting game results based on machine learning. Background technique [0002] At present, many methods based on strict mathematical statistics have emerged to predict the results of competitive games. According to the information we have, there are three authoritative prediction methods that are currently widely used to predict the outcome of football games. result: [0003] 1. ELO forecasting method [0004] The ELO prediction method was created by American physicist Dr. Aroad Elo. Dr. Elo first used this method to predict the outcome of a chess game. He described the method in detail in his book "Chess: Then and Now". Through the study of 1,500 Premier League games, Jaques Black made relentless improvements to the Elo prediction method, which is now It has been widely used in football matches. The improved model of the...

AI Technical Summary

Problems solved by technology

The generalization ability of the model is seriously insufficient, and it is impossible to evaluate the impact of unexpected random events on the game results (red and yellow cards, injuries, player conflicts, etc.)

Due to the inherent confrontational nature of football, it is a collection of "random processes" within 90 minutes. The prediction accuracy of the above model in the long-term window has no practical application value.

Images