AI-Based Anomaly Detection: Safeguarding Sports Integrity

In an article recently published in the journal Scientific Reports, researchers proposed a betting anomaly detection system based on artificial intelligence (AI) to eradicate illegal gambling and ensure integrity and fairness in sports.

Study: AI-Based Anomaly Detection: Safeguarding Sports Integrity. Image credit: matimix/Shutterstock
Study: AI-Based Anomaly Detection: Safeguarding Sports Integrity. Image credit: matimix/Shutterstock

Background

Sports events take place among competitors in a fair competition environment, which is governed by professional referees who make impartial judgments and rules for every game. In fair competitive environments, athlete-related internal factors, including physical conditions, ability, and effort, and external factors, including referee standards, field conditions, weather, and chance, determine the game results.

However, some individuals follow illegal practices, including doping/using banned substances and match-fixing, to predetermine the game results. Match-fixing refers to the act of officiating or playing a match to achieve a predetermined result. This is achieved by manipulating the internal conditions like coaches, opponents, or referees. Thus, match-fixing games can damage the spirit of sports and adversely impact the sports industry, which necessitates the development of match-fixing detection systems in sports.

Role of anomalies

In sports, anomalies refer to unusual or abnormal behaviors or patterns that deviate from the typical or expected behavior. In this study, anomalies were referred to the suspicious behaviors or activities indicating potential match-fixing. Match-fixing detection involves the identification and prevention of activities undermining the integrity and fairness of sports competitions.

Anomalies play a critical role in match-fixing detection as they manifest in different forms, like suspicious player behaviors, unexpected performance fluctuations, or unusual betting patterns. Thus, detecting anomalies is necessary as they raise potential match-fixing suspicions. The instances of manipulation can be identified, and proper action can be taken to ensure the sports competitions' fairness by analyzing the anomalies.

The proposed approach

In this study, researchers developed a solution to match-fixing in sports using different machine learning (ML) models to identify match-fixing anomalies based on betting odds. The objective of the study was to develop a match-fixing detection system in sports by leveraging an AI-based model to eliminate match-fixing in games and ensure integrity in games.

Five classification models, including the k-nearest neighbor (KNN) classification, support vector machine (SVM), random forest (RF), logistic regression (LR), and the ensemble model (a model optimized from the previous four models), were employed to distinguish between abnormal and normal matches. LR, KNN, RF, and SVM were selected for this study as they display robust performance in distinguishing abnormal and normal games based on lose odds, tie odds, and win odds patterns.

These models classified the abnormal and normal matches by learning their patterns using the sports betting odds data. The database was created using the world football league match betting data obtained from 12 betting companies, including Interwetten, 188bet, Vcbet, 12bet, Macauslot, Wewbet, Bet365, Crown, Easybet, Mansion88, Sbobet, and Willhill, which provided a vast amount of data on game schedules, teams, players, and league rankings for football matches.

Overall, 31 data types were collected that have an impact on the game outcome. An abnormal match detection model was developed based on each model's data analysis results using the match result dividend data. Then, data from real-time matches was utilized and the five models were applied to develop a system that can detect match-fixing in real-time.

Specifically, the abnormal betting detection model distinguished matches as abnormal, dangerous, caution, or normal based on the number of abnormal matches identified by the five ML models. Data from 20 matches, including 10 abnormal and 10 normal matches, were used to assess the developed match-fixing detection system.

K-league football matches and cases of match-fixing from 2000 and 2020 were utilized as data sources. The term "abnormal match" in this study referred to the games of match-fixing that happened between 2000 and 2020 that led to actual legal punishment, while the term "normal match" referred to the rest of the matches of the collected K-League dataset.

Significance of the study

Researchers successfully developed a sports match-fixing detection system based on AI using sports betting odds. Among the five classification models evaluated in this study, three models, including the ensemble, KNN, and RF, demonstrated a high accuracy of over 92%, while the SVM and LR models displayed 80% accuracy.

In comparison, previous studies using a single model to investigate football match betting odds data achieved 70-80% accuracy. Additionally, the AI-based match-fixing detection system developed to detect match-fixing in real-time showed 60% accuracy for abnormal matches and 80% accuracy for normal matches. To summarize, the findings of this study demonstrated the feasibility of using the AI-based match-fixing detection system as an effective preventive measure against match-fixing.

Journal reference:
Samudrapom Dam

Written by

Samudrapom Dam

Samudrapom Dam is a freelance scientific and business writer based in Kolkata, India. He has been writing articles related to business and scientific topics for more than one and a half years. He has extensive experience in writing about advanced technologies, information technology, machinery, metals and metal products, clean technologies, finance and banking, automotive, household products, and the aerospace industry. He is passionate about the latest developments in advanced technologies, the ways these developments can be implemented in a real-world situation, and how these developments can positively impact common people.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Dam, Samudrapom. (2024, March 25). AI-Based Anomaly Detection: Safeguarding Sports Integrity. AZoAi. Retrieved on October 08, 2024 from https://www.azoai.com/news/20240325/AI-Based-Anomaly-Detection-Safeguarding-Sports-Integrity.aspx.

  • MLA

    Dam, Samudrapom. "AI-Based Anomaly Detection: Safeguarding Sports Integrity". AZoAi. 08 October 2024. <https://www.azoai.com/news/20240325/AI-Based-Anomaly-Detection-Safeguarding-Sports-Integrity.aspx>.

  • Chicago

    Dam, Samudrapom. "AI-Based Anomaly Detection: Safeguarding Sports Integrity". AZoAi. https://www.azoai.com/news/20240325/AI-Based-Anomaly-Detection-Safeguarding-Sports-Integrity.aspx. (accessed October 08, 2024).

  • Harvard

    Dam, Samudrapom. 2024. AI-Based Anomaly Detection: Safeguarding Sports Integrity. AZoAi, viewed 08 October 2024, https://www.azoai.com/news/20240325/AI-Based-Anomaly-Detection-Safeguarding-Sports-Integrity.aspx.

Comments

The opinions expressed here are the views of the writer and do not necessarily reflect the views and opinions of AZoAi.
Post a new comment
Post

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.

You might also like...
AE-APT: Enhanced Detection of Advanced Cyber Threats