ORIGINAL RESEARCH article
Front. Artif. Intell.
Sec. Machine Learning and Artificial Intelligence
Generative AI-based approach for Player behaviour Analysis and Grey Area Identification
Provisionally accepted
Vinay K1*
Sriram Sankaran2- 1Amrita Vishwa Vidyapeetham University, Coimbatore, India
- 2Amrita Vishwa Vidyapeetham, Coimbatore, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Detecting exploitative or unethical player behaviour on an online gaming platform is challenging because of the presence of ambiguous grey case actions that are neither clearly defined as legitimate nor illegal. This study presents an interpretable behaviour analysis approach in conjunction with anomaly detection, synthetic data augmentation, and post hoc explainability to support human-based decision-making. Datasets collected from online multiplayer role-playing games (MMORPG Game) over several months were augmented using a CT-GAN (Conditional Table GAN) to address class imbalance, followed by anomaly detection using an EGBAD-based approach. This approach enhances transparency, and SHAP and LIME explanations are integrated to highlight feature-level contributions for grey cases. This approach resulted in improved detection performance over the baseline models, achieving higher F1-score and ROC-AUC scores with consistent gains across multiple runs.
Keywords: Bot detection, Explainable AI (SHAP,LIME), Generative AI (VAEs, GANs, CTGAN), Grey-area behaviours, Human-in-the-loop moderation, Online gaming ecosystems, player behaviour analysis
Received: 23 Oct 2025; Accepted: 30 Jan 2026.
Copyright: © 2026 K and Sankaran. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Vinay K
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.