Abstract
The interdisciplinary nature of sports and the presence of various systemic and non-systemic factors introduce challenges in predicting sports match outcomes using a single disciplinary approach. In contrast to previous studies that use sports performance metrics and statistical models, this study is the first to apply a deep learning approach in financial time series modeling to predict sports match outcomes. The proposed approach has two main components: a convolutional neural network (CNN) classifier for implicit pattern recognition and a logistic regression model for match outcome judgment. First, the raw data used in the prediction are derived from the betting market odds and actual scores of each game, which are transformed into sports candlesticks. Second, CNN is used to classify the candlesticks time series on a graphical basis. To this end, the original 1D time series are encoded into 2D matrix images using Gramian angular field and are then fed into the CNN classifier. In this way, the winning probability of each matchup team can be derived based on historically implied behavioral patterns. Third, to further consider the differences between strong and weak teams, the CNN classifier adjusts the probability of winning the match by using the logistic regression model and then makes a final judgment regarding the match outcome. We empirically test this approach using 18,944 National Football League game data spanning 32 years and find that using the individual historical data of each team in the CNN classifier for pattern recognition is better than using the data of all teams. The CNN in conjunction with the logistic regression judgment model outperforms the CNN in conjunction with SVM, Naïve Bayes, Adaboost, J48, and random forest, and its accuracy surpasses that of betting market prediction.
Highlights
Published: 18 July 2021Sports forecasting research has developed rapidly in recent years and begun to cover different sports, methods, and research questions
This paper proposes an approach for sports match outcome prediction with two main components: the convolutional neural network (CNN) classifier for implicit pattern recognition and the logistic regression model for matching outcome judgment
It revealed that when using OHLC time series to build a prediction model for sports matches, the CNN classifier with graphical classification to process the time series was not as accurate as the logistic regression model that took into account the strengths and weaknesses of the two teams
Summary
Published: 18 July 2021Sports forecasting research has developed rapidly in recent years and begun to cover different sports, methods, and research questions. Given that an improper setting of betting odds will bring huge losses to betting companies, the win/loss predictions implied in the odds are highly credible These odds are frequently adopted by researchers in economic and financial contexts and manipulated via a time series method to examine efficiency [10,11], study irrational behavior [12], and predict wins–losses [13,14] in betting markets. Such odds-based models mostly focus on how to beat bookmakers and measure performance based on the returns obtained from the predicted outcome in conjunction with the betting strategy [15], not pursuing the accuracy of the predictions [16]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have