Deep Multilayer Neural Network for Predicting the Winner of Football Matches (original) (raw)
Related papers
Football match prediction using deep learning
2017
In this thesis, the deep learning method Recurrent Neural Networks (RNNs) has been investigated for predicting the outcomes of football matches. The dataset consists of previous recorded matches from multiple seasons of leagues and tournaments from 63 different countries and 3 tournaments that include multiple countries. In the thesis work, we have studied several different ways of forming up input data sequences, as well as different LSTM architectures of RNNs that may lead to effective prediction, along with LSTM hyper-parameter tuning and testing. Extensive tests have been conducted through many case studies for the prediction and classification of football match winners. Using the proposed LSTM architectures, we show that the classification accuracy of the football outcome is 98.63% for many-to-one strategy, and 88.68% for manyto-many strategy. The prediction accuracy starts from 33.35% for many-to-one and 43.96% for many-to-many, and is increasing when more information about a ...
Deep learning for football outcomes prediction based on football rating system
10TH INTERNATIONAL CONFERENCE ON APPLIED SCIENCE AND TECHNOLOGY
The prediction models of association football can be categorized into three natural clusters, which are the statistical models, the machine learning and probabilistic graphical models and rating systems. The prediction may focus on matches outcomes prediction (win, draw and lose) or the number of goals scored obtained by home and away team. Match result prediction is very important as a benchmark for the management team to assess the chances of winning, drawing and losing for a particular team before the match starts. In the 2017 soccer challenge, the conventional machine learning and ensemble methods, as well as probabilistic graphical models such as k-Nearest Neighbor (k-NN), Gradient Boosting Tree (GBT) and Bayesian Networks (BN) have been a choice of researchers that participate the challenge and successfully dominate the challenge. Even so, there are some well-known techniques such as Neural Networks (NN) and Deep Neural Networks (DNN) that are left in this challenge although this technique has advantages in producing good results in many fields including solving real world problems which the results are comparable and sometimes superior to expert knowledge in some cases. In this paper, we propose a football match outcome prediction based on pirating system using TabNet, a DNN architecture for tabular data. The experiment cover two parts namely: (1) generates pirating system from 216,743 instances of raw football dataset and (2) predicts 206 football match outcomes using TabNet. As a result, the proposed prediction model based on the pirating system using TabNet successfully overcomes the existing model for football match outcomes for both scoring rules, in terms of accuracy and Rank Probability Score (RPS). The findings from this study are important because they can be used for future researchers in developing new football match outcome prediction models that incorporate several new features along with other features. This is important to improve the predictive performance of football prediction models using other advanced techniques.
Prediction of Football Games Results
2021
For creation of 3 machine learning models, dataset of 50, 100 and 200 games are being used. All the models are built, using deep learning (DL) and machine technology (ML) technique with the goal to prove, that even ML algorithms can be used to predict football games result. The data set consists of different real games results, collected from the most recognizable tournaments, such as: English Premier League, Italian Seria A, German Bundesliga, Spanish La Liga and French League 1. The target values of the work are prediction of exact game score (Average accuracy obtained after the last wave of testing – 11.6%) and prediction of game result (Average accuracy obtained after the last wave of testing – 39%).
A Comparative Study on Neural Network Based Soccer Result Prediction
Seventh International Conference on Intelligent Systems Design and Applications (ISDA 2007), 2007
This study mainly remarks the efficiency of blackbox modeling capacity of neural networks in the case of forecasting soccer match results, and opens up several debates on the nature of prediction and selection of input parameters. The selection of input parameters is a serious problem in soccer match prediction systems based on neural networks or statistical methods. Several input vector suggestions are implemented in literature which is mostly based on direct data from weekly charts. Here in this paper, two different input vector parameters have been tested via learning vector quantization networks in order to emphasize the importance of input parameter selection. The input vector parameters introduced in this study are plain and also meaningful when compared to other studies. The results of different approaches presented in this study are compared to each other, and also compared with the results of other neural network approaches and statistical methods in order to give an idea about the successful prediction performance. The paper is concluded with discussions about the nature of soccer match forecasting concept that may draw the interests of researchers willing to work in this area.
Can Machine Learning Predict Soccer Match Results?
Proceedings of the 11th International Conference on Agents and Artificial Intelligence, 2019
Sport result prediction proposes an interesting challenge considering as popular and widespread are sport games, for instance tennis and soccer. The outcome prediction is a difficult task because there are a lot of factors that can afflict the final results and most of them are related to the player human behaviour. In this paper we propose a new feature set (related to the match and to players) aimed to model a soccer match. The set is related to characteristics obtainable not only at the end of the match, but also when the match is in progress. We consider machine learning techniques to predict the results of the match and the number of goals, evaluating a dataset of real-world data obtained from the Italian Serie A league in the 2017-2018 season. Using the RandomForest algorithm we obtain a precision of 0.857 and a recall of 0.750 in won match prediction, while for the goal prediction we obtain a precision of 0.879 in the number of goal prediction less than two, and a precision of 0.8 in the number of goal prediction equal or greater to two.
Sensors, 2020
Predicting the results of soccer competitions and the contributions of match attributes, in particular, has gained popularity in recent years. Big data processing obtained from different sensors, cameras and analysis systems needs modern tools that can provide a deep understanding of the relationship between this huge amount of data produced by sensors and cameras, both linear and non-linear data. Using data mining tools does not appear sufficient to provide a deep understanding of the relationship between the match attributes and results and how to predict or optimize the results based upon performance variables. This study aimed to suggest a different approach to predict wins, losses and attributes’ sensitivities which enables the prediction of match results based on the most sensitive attributes that affect it as a second step. A radial basis function neural network model has successfully weighted the effectiveness of all match attributes and classified the team results into the ...
IRJET- Predicting Football Match Results using Machine Learning
IRJET, 2021
Analyzing statistics of football teams can help clubs predict their performance over a particular time frame. In this paper we use various machine learning algorithms to predict results of Premier League season 2017-2018 for home/away win or draw and analyze the important attributes that impact the full-time result. Games routinely gather information on how the player has the play. The knowledge is fed into an algorithm which is used by humans to pull games from its predictions of what players would see. Predictions help the manager of the squad to take the next step. By spotting weaknesses at the fighting team's defensive strategy, the weakness of a specific player or selecting the statistically most possible reaction to the move from past history, coaches might get an edge over their competition. We have done a comparative study between different machine learning algorithms and used the algorithm with the highest accuracy for our project.
Predicting the Outcome of English Premier League Matches using Machine Learning
2020 2nd International Conference on Sustainable Technologies for Industry 4.0 (STI), 2020
English Premier League (EPL) is the world’s most popular football league. Since this is a prominent league, there has been a variety of preceding endeavors both commercially and scholastically to predict EPL match results. In this paper, machine learning, a promising tool of the fourth industrial revolution (Industry 4.0), has been used to introduce a model for predicting the outcomes of EPL matches both in multi-class (home, draw, and away) and in binary-class (home, and not-home) with the last five seasons football matches. We have employed five machine learning algorithms along with different machine learning techniques ranging from data pre-processing to hyper-parameter optimization which find the best results. In addition, the comparative results demonstrate that, our proposed model gives 70.27% accuracy in multi-class and 77.43% accuracy in binary-class compared to the best known existing models in the literature.
Artificial Neural Network Approach to Football Score Prediction
2019
Sport betting companies and participants can maximize their profit in the sports betting business if they are able to accurately predict the outcome of football matches. This work seeks to develop such a football match prediction system with Manchester United football club as a case study. The developed system is based on an Artificial Neural Network (ANN) model. Scores from previous matches played by Manchester United were used to train and validate the network. The system has prediction accuracies of 73.72% and 113.5% for goals scored by, and against Manchester United respectively. The performance of the model is reasonably good but it can be improved by training the model with more football scores.