This study develops a solution to sports match-fixing using various machine-learning models to detect match-fixing anomalies, based on betting odds. We use five models to distinguish between normal and abnormal matches: logistic regression (LR), random forest (RF), support vector machine (SVM), the k-nearest neighbor (KNN) classification, and the ensemble model-a model optimized from the previous four. The models classify normal and abnormal matches by learning their patterns using sports betting odds data. The database was developed based on the world football league match betting data of 12 betting companies, which offered a vast collection of data on players, teams, game schedules, and league rankings for football matches. We develop an abnormal match detection model based on the data analysis results of each model, using the match result dividend data. We then use data from real-time matches and apply the five models to construct a system capable of detecting match-fixing in real time. The RF, KNN, and ensemble models recorded a high accuracy, over 92%, whereas the LR and SVM models were approximately 80% accurate. In comparison, previous studies have used a single model to examine football match betting odds data, with an accuracy of 70-80%.

Match-fixing, although not a new problem, has received growing attention during the COVID-19 pandemic, which has been reported in the media to have increased the risk of match-fixing events. Gambling is a well-documented addictive behavior, and gambling-related fraud, match-fixing, is a challenge to the world of sports. Most research on match-fixing has a judicial or institutional perspective, and few studies focus on its individual consequences. Nevertheless, athletes may be at particular risk of mental health consequences from the exposure to or involvement in match-fixing. The COVID-19 crisis puts a spotlight on match-fixing, as the world of competitive sports shut down or changed substantially due to pandemic-related restrictions. We call for research addressing individual mental health and psycho-social correlates of match-fixing, and their integration into research addressing problem gambling, related to the pandemic and beyond.

The growth of the online sports betting market has generated new risk areas and threats to sport integrity, such as match-fixing. In recent years, institutional concern to fight against the phenomenon has been intensified and a set of countermeasures has been adopted. One of the most widely implemented measures to protect integrity in sport is to ban athletes and sports players from betting on the competitions in which they are involved. In some countries, such as Portugal, this practice has become a crime under the new legislation. Despite the legal and sporting restrictions and the prevention programmes carried out for sport institutions to explain the gambling rules, there are many athletes who are putting bets on their own competitions and even in their own games. Through interviews with key informant actors and ethnographic fieldwork, this article describes betting patterns among sports actors in Portugal and explains the perceptions and incentives that lead them to bet in their own sports, competitions and games. The results show different conceptions of integrity between the normative discourse on legal and sport governance institutions and sports actors\' opinion, essentially, the premise that suggest a direct link between betting on one\'s own games and manipulation of these games. In some cases, betting in one\'s own games helps to strengthen fair play values. However, the spreading of online betting, together with the perception of inefficient controls in the implementation of sporting and legal regulations, creates opportunity structures for fixing matches and taking financial profit though gambling activities.