Academic Certificate Behavioral Fraud Detection: A Proof of Concept
- Publisher:
- Institute of Electrical and Electronics Engineers (IEEE)
- Publication Type:
- Conference Proceeding
- Citation:
- Proceedings of the 2026 20th International Conference on Ubiquitous Information Management and Communication Imcom 2026, 2026, 00, pp. 1-8
- Issue Date:
- 2026-01-01
Open Access
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
Academic certificate fraud has become problematic in this digital age. Insider threat in addition to the complex nature of today's fraudulent activities, underscore the need for advance fraud detection system. This paper proposes a novel approach to detect academic certificate fraud based on user behavior. The analysis of behavioral features facilitates improved detection of fraudulent activities in the certification process. Machine learning technique is employed to develop behavioral fraud detection model, with the assumption that user behaviors produce unique patterns. The activities that lead to issuing legitimate certificates may have consistent pattern. Any deviation from such pattern may be considered fraudulent. We used the publicly available enterprise access log dataset which is highly imbalanced with fraudulent instances less than 1%. The Synthetic Minority Over-Sampling Technique (SMOTE) was used to handle the class imbalance. As a proof-of-concept, we used logistic regression to develop our proposed model. Experimental results demonstrate the efficiency of the proposed approach by accurately distinguishing between legitimate and fraudulent certificates with a detection rate above 85%. This approach promises improved security against institutional certificate fraud. It also serves as a pre-registration fraud detection and prevention scheme for blockchain-enabled certificate system.
Please use this identifier to cite or link to this item: