Development of an Enhanced Financial Fraud Detection Model using a Machine Learning Algorithm

This study presents an enhanced financial fraud detection system that uses unsupervised machine learning techniques to identify anomalous financial transactions in highly imbalanced datasets. The increasing sophistication of digital financial fraud has reduced the effectiveness of traditional rule-based security systems, thereby necessitating adaptive and intelligent detection approaches. The proposed system uses the Isolation Forest algorithm for its computational efficiency and ability to detect previously unseen fraud patterns without relying on labelled data. A large transaction dataset comprising 284,807 financial records was preprocessed with normalization and dimensionality-reduction techniques prior to model training and evaluation. The developed model was integrated into a Flask-based web application that supports real-time transaction analysis via a user-friendly dashboard. Experimental results demonstrated strong predictive performance, achieving a recall of 94.7%, a precision of 53.5%, an F1 Score of 68.6%, and an ROC-AUC of 0.91. Comparative evaluation with One-Class SVM and Autoencoder models further revealed that while Autoencoders achieved slightly higher overall discrimination performance, Isolation Forest provided a more computationally lightweight and deployment-efficient solution for resource-constrained financial environments. The findings also highlight the practical implications of false positive management in fraud detection systems and emphasize the importance of balancing fraud sensitivity with operational efficiency. Overall, the study confirms that lightweight unsupervised anomaly detection models provide an adaptive, scalable, and deployable solution for enhancing financial security in modern fintech ecosystems.

Anomaly Detection, Isolation Forest, Financial Fraud, Machine Learning, Fintech, Real-time Monitoring.

1. Ahmed, M., Mahmood, A. N., & Hu, J. (2016). Survey of network anomaly detection techniques. Journal of Network and Computer Applications, 60, 19–31. [Google Scholar] [Crossref]

2. Arora, P., & Bhardwaj, A. (2025). A review of anomaly detection techniques in financial transactions: The move toward AI-driven solutions. International Journal of Financial Studies, 13(1), 45–58. [Google Scholar] [Crossref]

3. Bahnsen, A. C., Aouada, D., Ottersten, B., Stojanovic, J., & Žliobaitė, I. (2016). Cost-sensitive credit card fraud detection using Bayes minimum risk. Proceedings of the European Symposium on Artificial Neural Networks (ESANN), 1–6. [Google Scholar] [Crossref]

4. Bello, A., Omoniyi, T., & Hassan, M. (2023). The evolution of digital financial crimes in emerging economies: A review of cybersecurity threats in Nigeria. Journal of African Financial Technology, 14(2), 45–62. [Google Scholar] [Crossref]

5. Bhattacharyya, S., Jha, S., Tharakunnel, K., & Westland, J. C. (2011). Data mining for credit card fraud: A comparative study. Decision Support Systems, 50(3), 602–613. [Google Scholar] [Crossref]

6. Bolton, R. J., & Hand, D. J. (2002). Statistical fraud detection: A review. Statistical Science, 17(3), 235–255. [Google Scholar] [Crossref]

7. Carcillo, F., Dal Pozzolo, A., Le Borgne, Y. A., Caelen, O., Mazzer, Y., & Bontempi, G. (2019). Combining unsupervised and supervised learning in credit card fraud detection. Information Sciences, 557, 317–331. [Google Scholar] [Crossref]

8. Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), 1–58. [Google Scholar] [Crossref]

9. Dal Pozzolo, A., Caelen, O., Le Borgne, Y. A., Waterschoot, S., & Bontempi, G. (2015). Calibrating probability with undersampling for unbalanced classification. IEEE Symposium on Computational Intelligence and Data Mining (CIDM), 159–166. [Google Scholar] [Crossref]

10. Enehikhare, O., & Odumuyiwa, V. (2025). Addressing class imbalance in fraud detection datasets using synthetic oversampling and anomaly detection. Nigerian Journal of Computing and Applied Sciences, 7(4), 88–103. [Google Scholar] [Crossref]

11. Fatokun, J., Adeleke, R., & Ibrahim, S. (2025). Regulatory interventions and the persistence of electronic fraud in the Nigerian banking sector. Journal of Financial Regulation and Compliance (Africa Edition), 11(3), 201–218. [Google Scholar] [Crossref]

12. Fiore, U., De Santis, A., Perla, F., Zanetti, P., & Palmieri, F. (2019). Using generative autoencoders for detecting credit card fraud. Expert Systems with Applications, 132, 1–15. [Google Scholar] [Crossref]

13. Gandhar, A., Gupta, R., Sharma, P., & Verma, S. (2024). Machine learning and deep learning for financial security: The role of feature engineering and ensemble methods. Global Journal of Computer Science and Technology, 24(1), 12–29. [Google Scholar] [Crossref]

14. Liu, F. T., Ting, K. M., & Zhou, Z. H. (2008). Isolation Forest. Eighth IEEE International Conference on Data Mining, 413–422. [Google Scholar] [Crossref]

15. Nigeria Inter-Bank Settlement System (NIBSS). (2024). Electronic payment fact sheet and fraud landscape Q1-Q2 2024. NIBSS PublicaDufisan [Google Scholar] [Crossref]

16. Odufisan, K., Abhulimen, E., & Ogunti, E. (2025). Intelligence-driven defense: Enhancing fraud detection using context-aware machine learning models. West African Journal of Information Technology, 18(1), 15–34. [Google Scholar] [Crossref]

17. Onyeama, C. (2024). Unsupervised learning and autoencoders for financial anomaly detection: A Nigerian case study (Unpublished master's thesis)—University of Lagos, Nigeria. [Google Scholar] [Crossref]

18. Roy Devarakonda, S. (2023). Hybrid ML framework integrating isolation forests and autoencoders for anomaly detection. Journal of Big Data Analytics in Finance, 5(2), 77–94. [Google Scholar] [Crossref]

19. Sahin, Y., Bulkan, S., & Duman, E. (2013). A cost-sensitive decision tree approach for fraud detection. Expert Systems with Applications, 40(15), 5916–5923. [Google Scholar] [Crossref]

20. Sawant, A. (2025). Comparing supervised and unsupervised learning for detecting novel fraud patterns. TechScience Academic Review, 12(3), 210–225. [Google Scholar] [Crossref]

21. Zhang, Y., & Swarup, S. (2019). Feature engineering and regularized preprocessing dependencies in structural anomaly classifiers. IEEE Transactions on Knowledge and Data Engineering, 31(8), 1420–1434. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet