Fig 3 - uploaded by Laura Hervert
Content may be subject to copyright.
Context in source publication
Context 1
... equations correspond to the prior probability based on the adjusted start probability. The procedure for the soccer prediction using Bayesian function and shared history data is given in Figure 3. The probability taken for the prediction model is chosen between two options, shared history or ranking. ...
Similar publications
Resenha do livro Bibliofut: a literatura do futebol brasileiro (2019), de Domingos Antonio D’Angelo e Ademir Takara.
Citations
... Extensive studies have utilized various machine learning models across different sports disciplines. For instance, Hervert-Escobar et al. utilized a Bayesian learning model trained on a dataset comprising 200,000 soccer games to predict match outcomes, demonstrating the effectiveness of probabilistic models in sports predictions [1]. Similarly, Jain et al. developed a Hybrid Fuzzy-SVM model to forecast basketball game results, highlighting the utility of combining fuzzy logic with support vector machines for enhanced prediction accuracy [2]. ...
In competitive sports, there exists an intangible phenomenon known as “momentum” that significantly influences the dynamics of a game. Through the application of data analysis and machine learning techniques, this elusive concept of momentum can be quantified and leveraged to forecast game outcomes. Focusing on the domain of tennis, a linear model incorporating four parameters, which are selected based on the regulations and other intrinsic attributes of tennis matches, is devised to encapsulate player performance. By definition, the exponential weighted moving average of player performance serves as a robust metric for measuring momentum, validated through correlation testing. Subsequently, utilizing logistic regression and simulation algorithms, a predictive model is constructed to forecast game progression at both discrete points and the ultimate match result. Experimental findings indicate a high degree of alignment between the model predictions and the actual flow of the game.
... In Soccer, features used in predictive models include dimensionality reduction, classifier combinations, historical patterns, team rankings, player attributes, spatio-temporal trajectory frames, event stream data, and player profiles. Studies by Tax and Joustra (2015), Hervert-Escobar et al. (2018b), and Wang et al. (2024) utilized these features to improve the accuracy and predictive performance of the model. ...
... In Soccer, performance metrics include prediction accuracy, McNemar's test, RPS, top-3 accuracy, F1 score, human expert assessments, AP, precision, recall, AUC, BIC, RMSE, and cross-entropy. Studies by Tax and Joustra (2015), Hervert-Escobar et al. (2018b), and Wang et al. (2024) utilized these metrics to evaluate the performance of the model. ...
The sports betting industry has experienced rapid growth, driven largely by technological advancements and the proliferation of online platforms. Machine learning (ML) has played a pivotal role in the transformation of this sector by enabling more accurate predictions, dynamic odds-setting, and enhanced risk management for both bookmakers and bettors. This systematic review explores various ML techniques, including support vector machines, random forests, and neural networks, as applied in different sports such as soccer, basketball, tennis, and cricket. These models utilize historical data, in-game statistics, and real-time information to optimize betting strategies and identify value bets, ultimately improving profitability. For bookmakers, ML facilitates dynamic odds adjustment and effective risk management, while bettors leverage data-driven insights to exploit market inefficiencies. This review also underscores the role of ML in fraud detection, where anomaly detection models are used to identify suspicious betting patterns. Despite these advancements, challenges such as data quality, real-time decision-making, and the inherent unpredictability of sports outcomes remain. Ethical concerns related to transparency and fairness are also of significant importance. Future research should focus on developing adaptive models that integrate multimodal data and manage risk in a manner akin to financial portfolios. This review provides a comprehensive examination of the current applications of ML in sports betting, and highlights both the potential and the limitations of these technologies.
... We compare the three models earlier explained, along with Hervert's Bayes Model (Hervert-Escobar et al., 2018) in terms of accuracy as seen in Table 1. Meanwhile, Table 2. ...
This study brings back the concept of weak-form efficiency in soccer betting markets. In sports, for odds to show efficiency as the ground truth of their price, they must reflect all historical information relevant to the match outcome probabilities. The aim is to show weak-form efficiency by dismissing closing odds on the winning probability model and to propose a Machine Learning pipeline on game state information previous to the match. The novelty presented in this work is to prove relevance to the wisdom of the crowds on Twitter by applying Sentiment Analysis.
Estimating the soccer match outcome with adequate accuracy is still one of the biggest challenges in the sports domain. In this work, the proposed novel Intelligent Strategic Planning Method based Algorithm (ISPMA) carries out dynamic estimation of soccer team performance in terms of the match outcome and noticeably outperforms the existing state of the art methods due to its unique features. In this work, the output of the four feature selection machine learning techniques i.e. Pearson correlation, forward selection, Extra tree classifier, and CHI-square is firstly unified before feeding these selected features as an input to the seven classifiers i.e. SVM (Support Vector Machine), Naïve Bayes, KNN (K-Nearest Neighbor.), Decision Tree, Random Forest, Logistic Regression, and AdaBoost. The dataset comprises eleven seasons of the English premier league and 3762 matches have been used to train the model and 418 matches to test the same. Such a reasonable size of soccer dataset is not common in previous studies. Another unique feature of this work is the time of estimation as estimation can be done during the progression of the game based on match statistics associated with the first half of the match. The proposed method uses a novel approach by computing the average values of the selected set of features for the victory of the team to estimate match results. By using these computed average values, ISPMA generates strategic planning based suggestions for the second half of the match. The strategic planning generated by the proposed method facilitates estimating the team performance and shifting the momentum from one team to another and can assist the coach, managers, and the team in carrying out effective decision-making for better match outcome.
Sports research and betting have been powered by quick exposure to the Internet and machine learning popularity. Football is considered the most popular game in 200 countries and contrasts to other sports. It is considered much more diverse and complicated, making soccer an enticing area to do research. A variety of methodologies and methods are used for the production of prediction systems. We expect the outcome of a match between the Premier League and a home side. The projections are based on numerous significant evidences from the Premier League’s previous seasons. These essential characteristics would possibly decide the result of a match. We use three different algorithms to predict the machine learning techniques and then choose from those three the best algorithm for predicting the label.
Applying Machine learning, data analytics etc have proven a greater improvement in decision making in all levels. A special attention has been made in the field of sports. As a whole, team improvement is a main concerned in all directions. The goal of any team would be to win every match they play. This can happen only if there is an excellent team efforts i.e. good coordination between players. We propose Sports Analysis an approach for better performance day by day. In this paper we talk about acquiring the details of a match and presenting team statistics.
