一种体育运动结果预测的机器学习框架设计  

A Machine Learning Framework For Predicting Sports Results

作　　者：校力[1] XIAO Li(Sports Institute of xianyang Vocational Technical College, Xianyang 712000 China)

机构地区：[1]咸阳职业技术学院体育学院

出　　处：《自动化技术与应用》2019年第9期59-62,87,共5页Techniques of Automation and Applications

摘　　要：机器学习(Machine Learning,ML)是一种智能方法,在分类和预测领域起到了良好的作用,在体育预测领域需要准备的预测结果,这是由于在大型的体育赛事中赌球涉及了大量的金钱。同时,体育专业俱乐部经理和老板都在努力建立分类模型,以便他们能够理解和制定赢得比赛所需的策略,这些模型涉及了比赛相关的众多因素,如历史比赛结果、玩家表现指标和对手信息等。本文主要对ML文献进行了详细的分析,重点研究了人工神经网络(Artificial Neural Network,ANN)在运动结果预测中的应用,并且确定了所使用的学习方法、数据来源、模型评估的适当方法以及预测运动结果的具体挑战。本文所提出的运动预测框架,将ML作为一种学习策略。Machine Learning (ML) is an intelligent method, which plays a good role in the field of classification and prediction. In the field of sports prediction, the prediction results need to be prepared, which is due to the large amount of money involved in gambling in large sports events. At the same time, sports club managers and owners are working hard to build classification models so that they can understand and formulate strategies to win games. These models involve many factors related to the games, such as historical game results, player performance indicators and opponent information. In this paper, a detailed analysis is carried out on the ML literature, with emphasis on the application of Artificial Neural Network (ANN) in the prediction of motion results, and the learning methods, data sources, appropriate methods for model evaluation and specific challenges for predicting the motion results are determined. The motion prediction framework proposes in this paper USES ML as a learning strategy.

关 键 词：机器学习 体育预测领域 人工神经网络 框架 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]