Predição de resultados em partidas de futebol utilizando Deep Learning
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| تاريخ النشر: | 2023 |
| التنسيق: | Bachelor thesis |
| اللغة: | por |
| المصدر: | Repositório Institucional da UPF |
| Download full: | https://repositorio.upf.br/handle/123456789/7482 |
الملخص: | This paper aims to present a study on the prediction of results in Premier League football matches using Deep Learning techniques, specificallyMultilayer Perceptron Neural Network (MLP), in order to contribute to sports data analysis and the prediction of football match outcomes, and to use them in online betting platforms. The prediction of results is carried out in two ways: in the first approach, the network predicts a home team win (0), a draw (1), or an away team win (2), achieving an accuracy of 53.65% in this context. In the second approach, only whether the home team wins (0) or not (1) is considered, resulting in an accuracy of 64.23%. Additionally, a simulation was conducted based on the pre-match odds of the games to analyze whether the bettor would profit or incur losses. In the first format, the simulation showed a loss of R$ -266.41 for a bet of R$ 548.00, while in the second format, a loss of R$ -58.91 was incurred for the same amount. These results suggest that the use of the MLP algorithm can be effective only as an aid in decision-making for predicting football match outcomes, as considering the predicted data would result in losses for the bettor. |
مواد مشابهة: Predição de resultados em partidas de futebol utilizando Deep Learning
- Rice crop detection using LSTM, Bi-LSTM, and machine learning models from sentinel-1 time series
- Using AI for forecasting and trading in markets : a study of deep learning and deep reinforcement learning in finance
- Bayesian optimization for stake allocation in soccer betting
- SCAN-NF : a machine learning system for invoice product trasaction classification through short-text processing
- Deep learning based objective quality assessment of multidimensional visual content
- Classificação de intensidade das emoções na fala em português brasileiro por meio de deep learning