SACNN: Self Attention-based Convolutional Neural Network for Fraudulent Behaviour Detection in Sports
SACNN: Self Attention-based Convolutional Neural Network for Fraudulent Behaviour Detection in Sports
Maxx Richard Rahman, Lotfy Abdel Khaliq, Thomas Piper, Hans Geyer, Tristan Equey, Norbert Baume, Reid Aikin, Wolfgang Maass
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Main Track. Pages 6017-6025.
https://doi.org/10.24963/ijcai.2024/665
Doping practices in sports by unscrupulous athletes have been an important societal issue for several decades. Recently, sample swapping has been raised as a potential practice performed by athletes to swap their doped samples with clean samples to evade the positive doping test. So far, the only proven method to detect such cases is by performing DNA analysis on samples. However, it is expensive and time-consuming, which goes beyond the budgetary limits of anti-doping organisations when implementing to all the samples collected during sports events. Therefore, in this paper, we propose a self attention-based convolutional neural network (SACNN) that incorporates both spatial and temporal behaviour of the longitudinal profile and generates embedding maps for solving the fraud detection problem in sports. We conduct extensive experiments on the real-world datasets. The result shows that SACNN outperforms other state-of-the-art baseline models for sequential anomaly detection. Moreover, we conduct a study with domain experts on real-world profiles using both DNA analysis and our proposed method; the result demonstrates the effectiveness of our proposed method and the impact it could bring to the society.
Keywords:
Multidisciplinary Topics and Applications: MTA: Sports
Machine Learning: ML: Applications
AI Ethics, Trust, Fairness: ETF: Societal impact of AI