Authors : Rebecca Ugonna Ugoha; Chukwu Peter Chijioke; Rosemary Chinyere Okolie; Cosmas Ifeanyi Nwakanma; Stanley Adiele Okolie; Onyemauche; Atumonyego Patricia Chiamaka

Volume/Issue : Volume 11 - 2026, Issue 2 - February

Google Scholar : https://tinyurl.com/ymhej2zj

Scribd : https://tinyurl.com/39m5avkf

DOI : https://doi.org/10.38124/ijisrt/26feb422

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Identity theft in e commerce transactions results to a significant cybersecurity challenge with worldwide fraud losses exceeding 32 billion in 2022. Traditional rule based detection systems lacks flexibility while machine learning methods face transparency issues critical to regulatory compliance. This paper introduces an ontology based fraud detection framework using OWL 2 and SWRL to capture semantic relationships in e commerce transactions. The system encodes domain knowledge through 2 core classes and 23 properties creating understandable detection rules through semantic reasoning. Testing with synthetic data shows 91 percent precision and 88 percent recall with an average reasoning time of 5.4 seconds for 150 transactions. The framework identified 71 semantic axioms offering traceable decision paths for each classification. Although current scalability limits real time use this approach provides a foundation for explainable AI in financial fraud detection.

References :

1. Statista, “The exponential increase in online transactions,” 2022.
2. Adamu et al., “Elaboration of financial fraud ontology,” 2022.
3. Brown and Williams, “Rule-based fraud detection limitations,” 2020.
4. Hasan, “Machine learning in online fraud detection,” 2024.
5. Chowdhury, “Advancing fraud detection through deep learning,” 2024.
6. Damian Chukwujekwu et al., “Ensemble methods for financial fraud detection,” 2024.
7. Siddique, “Hybrid ML + DL models for fraud detection,” 2025.
8. Ion Grujdin and Datcu, “Heterogeneous GNNs with graph attention for fraud detection,” 2025.
9. Ziyi Zhang et al., “Identity fraud detection through user behavior data,” 2025.
10. Green and Davis, “Challenges in interpretability of ML models,” 2020.
11. Orche and Bahaj, “Ontology-based fraud detection in electronic payment systems,” 2020.
12. Kainat Ansar et al., “Ontology-based alert model for financial fraud,” 2025.
13. Ada John et al., “Combining ontologies and neural networks for payment fraud detection,” 2025.
14. Li-Ming Chen et al., “Ontology-based reasoning for detecting misstatement accounts,” 2025.
15. Saritha Crasta and Janefer, “E-commerce identity fraud detection,” 2025.
16. Ritesh Chandra et al., “Ontology-driven big data analytics: scalability and maintenance,” 2025.
17. Otieno, “Data protection and privacy in e-commerce environments,” 2025.