Abstract
Match outcome prediction is a challenging problem that has led to the recent rise in machine learning being adopted and receiving significant interest from researchers in data science and sports. This study explores predictability in match outcomes using machine learning and candlestick charts, which have been used for stock market technical analysis. We compile candlestick charts based on betting market data and consider the character of the candlestick charts as features in our predictive model rather than the performance indicators used in the technical and tactical analysis in most studies. The predictions are investigated as two types of problems, namely, the classification of wins and losses and the regression of the winning/losing margin. Both are examined using various methods of machine learning, such as ensemble learning, support vector machines and neural networks. The effectiveness of our proposed approach is evaluated with a dataset of 13261 instances over 32 seasons in the National Football League. The results reveal that the random subspace method for regression achieves the best accuracy rate of 68.4%. The candlestick charts of betting market data can enable promising results of match outcome prediction based on pattern recognition by machine learning, without limitations regarding the specific knowledge required for various kinds of sports.
Highlights
Many people focus their attention on the outcomes of sports events
The results demonstrate that betting odds and margins have a rather high predictive accuracy, which is justified because bookmakers cannot survive on inefficient odds and margins
This study explores whether odds, scores and the derived candlestick chart can be used to predict the outcome of a match
Summary
Many people focus their attention on the outcomes of sports events. A match result has a significant impact on players, coaches, sports fans, journalists and bookmakers. In recent years, detailed data gathered during games and the box scores of every competition in various sports have been systematically recorded and stored in databases. Given the vigorous development of machine learning technology, these databases have gradually gained attention, and classic sports analysis and prediction, such as technical and tactical analysis, offensive/defensive strategy analysis and opponent scouting, have extended to the field of the application of big data. Many historical game performances of teams and players, as well as a wide variety of game-related data, have been used as a feed for machine learning modelling to enable prediction. Applying machine learning modelling and different data processing methods to various sports leads to different predicting accuracies. The adaptability of machine learning for predicting the outcome of a given sports competition is an important research topic
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
