Volume 11 - Summer Supplementary
Ann Appl Sport Sci 2023, 11 - Summer Supplementary: 0-0 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Kim C, Park J, Kim D, Lee J. Detectability of Sports Betting Anomalies Using Deep Learning-based ResNet: Utilization of K-League Data in South Korea. Ann Appl Sport Sci 2023; 11 (S1)
URL: http://aassjournal.com/article-1-1158-en.html
URL: http://aassjournal.com/article-1-1158-en.html
1- Center for Sports and Performance Analysis, Korea National Sport University, Seoul, Republic of Korea
2- Center for Sports and Performance Analysis, Korea National Sport University, Seoul, Republic of Korea ,jylee882@naver.com
2- Center for Sports and Performance Analysis, Korea National Sport University, Seoul, Republic of Korea ,
Abstract: (2347 Views)
Background. Sports match-fixing refers to the act of pre-determining the results of a game. Match-fixing fundamentally undermines competition in sports, and it harms society as a whole. Match-fixing has large as it is conducted as a secret transaction. Consequently, finding evidence regarding this illegal activity or detecting it is difficult. Therefore, a system should be built to detect match-fixing to prevent it.
Objectives. This study aims to detect betting anomalies in sports events through dividend graphs.
Methods. We collected the odds data for the K-League from 2010 to 2020 and converted the data into graph images to generate 3101 graph images. The collected data was analyzed using ResNet to classify them into normal games (2,464 games) and abnormal games (637 games) based on an image classification method. The ResNet model was trained for 100 epochs, and as a result, values below 0.05 were derived as the loss values of the training and test data, respectively.
Results. After performing the validation with the test data of 50 normal and 27 abnormal games, it was found that the accuracy in deriving normal games was 90%. Furthermore, match-fixing games were derived with an accuracy of 74.1%. Therefore, the model was accurate for 65 out of 77 games, showing that the model’s accuracy was 84.44%.
Conclusion. The results demonstrate the model’s value as a method for detecting sports match-fixing. Additionally, it can aid in eradicating sports match-fixing by providing the basic data for undertaking detailed match-fixing investigations.
Objectives. This study aims to detect betting anomalies in sports events through dividend graphs.
Methods. We collected the odds data for the K-League from 2010 to 2020 and converted the data into graph images to generate 3101 graph images. The collected data was analyzed using ResNet to classify them into normal games (2,464 games) and abnormal games (637 games) based on an image classification method. The ResNet model was trained for 100 epochs, and as a result, values below 0.05 were derived as the loss values of the training and test data, respectively.
Results. After performing the validation with the test data of 50 normal and 27 abnormal games, it was found that the accuracy in deriving normal games was 90%. Furthermore, match-fixing games were derived with an accuracy of 74.1%. Therefore, the model was accurate for 65 out of 77 games, showing that the model’s accuracy was 84.44%.
Conclusion. The results demonstrate the model’s value as a method for detecting sports match-fixing. Additionally, it can aid in eradicating sports match-fixing by providing the basic data for undertaking detailed match-fixing investigations.
Full-Text [PDF 782 kb]
(1347 Downloads)
APPLICABLE REMARKS
APPLICABLE REMARKS
• The result of this study is valuable as basic data for detecting match-fixing in sports.
• This study can be presented as a solution to eradicate sports match-fixing.
• This study can be presented as a solution to eradicate sports match-fixing.
Type of Study: Original Article |
Subject:
Motor Control and its Related Branches
Received: 2022/09/5 | Accepted: 2022/10/18
Received: 2022/09/5 | Accepted: 2022/10/18
References
1. Aleskerov E, Freisleben B, Rao RB. CARDWATCH: a neural network based database mining system for credit card fraud detection. Proceedings of the IEEE/IAFE 1997 Computational Intel-ligence for Financial Engineering (CIFEr), 1997;220-226.
2. Kumar R. Risk factors in cost estimation: building contractors' experience. Am J Civ Eng. 2005; 6:123-128. [DOI:10.12691/ajcea-6-3-5]
3. Spence C. Parra L, Sajda, P. Detection, Synthesis and Compression in Mammographic Image Analysis with a Hierarchical Image Probability Model. Proceedings IEEE Workshop on Mathe-matical Methods in Biomedical Image Analysis (MMBIA 2001), 2001;991693:3-10. [DOI:10.1109/MMBIA.2001.991693]
4. Choi CH, Park JH. The possibility of detecting match-fixing: Benford's Law in sports data. Ko-rean J. Meas Eval Phys Educ Sport Sci. 2017;19:69-89. [DOI:10.21797/ksme.2017.19.1.007]
5. Park SY, Yoon CC. The ethical sensitivity level of domestic badminton athletes for match-fixing. Sport Sci. 2021;39:395-402. [DOI:10.46394/ISS.39.3.45]
6. Chang YC, Lee GH. A study on the cause analysis of sports ethical deviance. Korean J Sport Sci. 2016;25:15-29.
7. Park, JH, Choi CH, Cho E. Preliminary study to detect match-fixing: Benford's law in badminton rally data. J Phys Educ. 2016;3:64-77.
8. Duggan M, Levitt SD. Winning isn't everything: Corruption in sumo wrestling. Am Econ Rev. 2002;92:1594-1605. [DOI:10.1257/000282802762024665]
9. Van RB. The odds of match fixing-Facts & figures on the integrity risk of certain sports bets. Available at SSRN 2015, 2555037.
10. Marchetti F, Reppold FAR, Constandt B. At risk: Betting-related match-fixing in Brazilian foot-ball. Crime Law Soc Change. 2021;76:431-450. [DOI:10.1007/s10611-021-09971-0]
11. Ötting M, Langrock R, Deutscher C. Integrating multiple data sources in match-fixing warning systems. Stat Modelling. 2018;18:483-504 [DOI:10.1177/1471082X18804933]
12. Park SK. Sports manipulation and criminal responsibility. J Sports Entertain L. 2011;14:217-242. [DOI:10.19051/kasel.2011.14.3.217]
13. Fiore U, De Santis A, Perla F, Zanetti P, Palmieri F. Using generative adversarial networks for improving classification effectiveness in credit card fraud detection. Inf Sci. 2019;479:448-455. [DOI:10.1016/j.ins.2017.12.030]
14. Pumsirirat A, Liu Y. Credit card fraud detection using deep learning based on auto-encoder and restricted Holtzmann machine. Int J Adv Comput Sci Appl. 2018; 9. [DOI:10.14569/IJACSA.2018.090103]
15. Roy A, Sun J, Mahoney R, Alonzi, L, Adams S, Beling P. Deep learning detecting fraud in credit card transactions. IEEE In 2018 Systems and Information Engineering Design Symposium (SIEDS) 2018:129-134. [DOI:10.1109/SIEDS.2018.8374722]
16. Wang Y, Xu W. Leveraging deep learning with LDA-based text analytics to detect automobile insurance fraud. Decis Support Syst. 2018;105:87-95. [DOI:10.1016/j.dss.2017.11.001]
17. Sun L, Cao, B, Wang, J, Srisa-an, W, Philip SY, Leow AD, Checkoway S. Kollector: Detecting fraudulent activities on mobile devices using deep learning. IEEE Trans Mob Com-put. 2020;20:1465-1476. [DOI:10.1109/TMC.2020.2964226]
18. Krizhevsky, A.; Sutskever, I.; Hinton, G. E. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25.
19. Igami, M. Artificial intelligence as structural estimation: Economic interpretations of Deep Blue, Bonanza, and AlphaGo 2018; 1710.10967.
20. Ha TY, Lee HJ. Presenting Direction for the Implementation of Personal Movement Trainer through Artificial Intelligence based Behavior Recognition. J of the Korea Convergence Society. 2019;10:235-242..
21. Park JY, KIM JS, Woo YT. A motion classification and retrieval system in baseball sports video using Convolutional Neural Network model. J of The Korea Society Computer And Information. 2021;26:31-37
22. Håkansson A, Jönsson, C, Kenttä G. Match-fixing causing harm to athletes on a COVID-19-influenced gambling market: a call for research during the pandemic and be-yond. Front Psychol. 2021;12:712300. URL: http://10.3389/fpsyg.2021.712300 [DOI:10.3389/fpsyg.2021.712300] [PMID] [PMCID]
23. Hatfield O. Statistical methods for detecting match-fixing in tennis. Lancaster University (Unit-ed Kingdom). 2019. URL:https://www.proquest.com/openview/2c2082762909d6a81832dc309670c1d3/1?pq-origsite=gscholar&cbl=18750&diss=y
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
