Data Analytics for Uncovering Fraudulent Behaviour in Elite Sports

Maxx Richard Rahman, Thomas Piper, Hans Geyer, Tristan Equey, Norbert Baume, Reid Aikin, Wolfgang Maass

Abstract: Description Sports officials around the world are facing societal challenges due to the unfair nature of fraudulent practices performed by unscrupulous athletes. Recently, sample swapping has been raised as a potential practice where some athletes exchange their doped sample with a clean one to evade a positive test. The current detection method for such cases includes laboratory testing like DNA analysis. However, these methods are costly and time-consuming, which goes beyond the budgetary limits of anti-doping organisations. Therefore, there is a need to explore alternative methods to improve decision-making. We presented a data analytical methodology that supports anti-doping decision-makers on the task of athlete disambiguation. Our proposed model helps identify the swapped sample, which outperforms the current state-of-the-art method and different baseline models. The evaluation on real-world sample swapping cases shows promising results that help advance the research on the application of data analytics in the context of anti-doping analysis.