Cognitive Cyber Crimes in the Era of Artificial Intelligence

2Detecting and Preventing Synthetic Identity Fraud and Mapping

Davinder Singh Gill¹, Mirza Shuja², Tapan Kant³ and Mukesh Kumar⁴*

¹Department of Computer Application, Chandigarh School of Business, Chandigarh Group of Colleges Jhanjeri, Mohali, Punjab, India

²Department of Computer Applications, Lovely Professional University, Punjab, India

³Department of CEA, GLA University, Mathura, Uttar Pradesh, India

⁴Advanced Centre of Research & Innovation (ACRI), Department of Computer Application, Chandigarh School of Business, Chandigarh Group of Colleges Jhanjeri, Mohali, Punjab, India

Abstract

Synthetic identity fraud is a fast-growing threat in the financial ecosystem, where criminals fabricate fictitious identities by combining real and fake information. This study proposes a novel detection and prevention framework utilizing the Credit Card Fraud Detection Dataset. The proposed approach integrates isolation forest and gradient boosting classifiers, optimized using hyperparameter tuning, to detect anomalous identity patterns. Additionally, an identity-linking algorithm based on graph mapping has been implemented to visualize connections among fraud attempts. The proposed method achieved a detection accuracy of 98.7%, a precision of 96.2%, recall of 97.4%, and an F1 score of 96.8%. These results demonstrate the potential of the model in both detection and mapping of synthetic identity fraud networks.

Keywords: Synthetic identity fraud, isolation forest, gradient boosting, identity ...