Sports events take place in an environment of fair competition among competitors governed by rules for each game and professional referees who make fair judgments. In a fair, competitive environment, game results are determined by internal factors related to the athletes, including physical ability, effort, and conditions, as well as external factors, such as chance, weather, field conditions, and referee standards. 

The public watches sports enthusiastically because of the excitement and uncertainty of the results under various conditions and the belief that the players did their best under fair conditions. However, it is challenging for athletes to increase their competence and consistently train to perform at the highest level. Efforts to ensure fairness in sports are ongoing. To ensure fairness and equal chances of winning for all contestants, regardless of different physical abilities, athletes are classified by gender and weight in some sports and by age in others to ensure equality of opportunity, regardless of differences in cognitive ability.

Unfortunately, some people aim to predetermine sports results through illegal practices. Typical illegal practices include “doping”—the use of banned substances, such as performance-enhancing drugs in competitive sports, and match-fixing—the act of playing or officiating a match to achieve a predetermined result by manipulating internal conditions, such as referees, opponents, or coaches.

Understanding the market risks

Match fixing in sports could create enormous profits for those involved in corrupt activities; however, it has significant negative consequences, such as threatening the integrity of the sport and causing fans to leave. Although people love sports for various reasons, the excitement and uncertainty of the results are at the core of this love.

Chance factors, such as player conditions during the game, influence the match result. The public is enthusiastic about sports and cheers for the athletes. If the match results are manipulated and predetermined, the public will abandon sports, and athletes will lose their motivation to compete.

Continued match fixing could substantially negatively influence sports, and the industry will inevitably shrink. It is, therefore, crucial to detect anomalies and match-fixing to protect the future of sports and athletes.

AI to prevent match fixing

Researchers Changgyun Kim, Jae-Hyeon Park & Ji-Yong Lee tested the performance of AI models in detecting illegal gambling in sports. Five models were tested using data from 20 matches (ten regular and ten abnormal). K-league football matches and match fixing cases between 2000 and 2020 were used as data sources. 

In this study, the term “abnormal match” refers to games of match-fixing that occurred between 2000 and 2020 and resulted in actual legal punishment. “Normal match” refers to the remaining matches in the K-League dataset collected. A game was classified as abnormal if the class assigned by each model contained four or more abnormal cases. Likewise, if three cases were classified as cautions, the game was classified accordingly.

In sports, match fixing issues tend to occur constantly and damage the fundamental value of fairness. Various methods have been proposed to solve this problem. Efforts have been made to build a match fixing anomaly-detection model using match data.

The study utilized only actual, real-world data. When a match is flagged as irregular, it is concrete evidence of misconduct. Such fraudulent activities are compassionate and present substantial challenges in large-scale data collection. Furthermore, even if an unusual pattern emerges in a typical match, its value as verification data diminishes unless confirmed as an irregularity resulting from foul play.

Key findings of the research

The study published aimed to develop an AI-powered sports match-fixing detection system using sports betting odds. Five models in this study achieved an accuracy of over 90%, while two demonstrated an accuracy of approximately 80%.

Real-time match data were collected, and the five models were applied to build a system to detect match fixing in real-time. The performance of the developed system was validated using ten regular matches and ten abnormal matches. The results showed an accuracy of 80% for regular matches and 60% for abnormal matches.

In short, the study provides an effective preventive measure—an AI-based system against match fixing, which undermines sports fairness and negatively impacts the sports industry. 

Image source: Unspalsh

Content Source: Research paper published in Nature