Identifying Gambling Risk Profiles from Online Behavioral Data: An AI Cluster-Based Empirical Study

  • Arthur C. S. Xavier Futuro Tech
  • Milton T. M. Junior Futuro Tech
  • Hendrik W. C. Garcia FPS
  • Adriana F. G. Barreto Futuro Tech
  • Tiago A. E. Ferreira UFRPE

Resumo


This study investigates whether behavioral risk profiles can be identified using clustering techniques applied to real-world player tracking data. Only in 2023, more than 7% of the Brazilian population was classified as high risk for problematic gambling. Behavioral indicators were extracted from the transactional data of more than 11,000 gamblers from a Brazilian online operator and used to train a K-Means clustering model. The resulting clusters were evaluated using a daily monitoring dataset and compared with a group of voluntary self-excluded players. The results show that approximately 89% of these players were classified in the high-risk clusters at least once, indicating that the proposed indicators capture behavioral patterns associated with gambling risk.

Referências

American Psychiatric Association (2022). Diagnostic and Statistical Manual of Mental Disorders: DSM-5-TR. American Psychiatric Association Publishing, Washington, DC.

Auer, M. and Griffiths, M. D. (2023). An empirical attempt to operationalize chasing losses in gambling utilizing account-based player tracking data. Journal of Gambling Studies, 39:1547–1561.

Banco Central do Brasil (2024). Análise técnica sobre o mercado de apostas online no brasil e o perfil dos apostadores [technical analysis of the online betting market in brazil and the profile of bettors]. Estudo Especial 119, Banco Central do Brasil, Brasília.

Bijker, R., Booth, N., Merkouris, S. S., and et al. (2023). International prevalence of self-exclusion from gambling: a systematic review and meta-analysis. Current Addiction Reports, 10:844–859.

Catania, M. and Griffiths, M. (2021). Applying the dsm-5 criteria for gambling disorder to online gambling account-based tracking data: An empirical study utilizing cluster analysis. Journal of Gambling Studies, 38:1–18.

Universidade Federal de São Paulo (UNIFESP) (2025). Caderno Temático LENAD III: Jogos de Aposta na População Brasileira – Resultados 2023 [LENAD III Thematic Report: Gambling in the Brazilian Population – 2023 Results]. UNIAD/UNIFESP, São Paulo.
Publicado
01/06/2026
XAVIER, Arthur C. S.; M. JUNIOR, Milton T.; GARCIA, Hendrik W. C.; BARRETO, Adriana F. G.; FERREIRA, Tiago A. E.. Identifying Gambling Risk Profiles from Online Behavioral Data: An AI Cluster-Based Empirical Study. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 26. , 2026, Ouro Preto/MG. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2026 . p. 1427-1432. ISSN 2763-8952. DOI: https://doi.org/10.5753/sbcas.2026.21559.