ABSTRACT
With the rise in technology, the rates of fraudulent activities are significantly increasing, causing threat and reputation at stake to individuals, industries, and the global economies. Conventional approach for predicting financial fraud has been obsolete due to its static method as the fraud tactic changes, and also lack of adaptation, efficiency, and poor predictive performance. To tackle this challenge, this paper proposes SynoBoost-LuminoFeatML model, which incorporates the innovative SynBoost for handling data imbalance and LuminoFeat for the optimal selection of Features. For SynBoost is developed with a hybrid sampling technique, incorporating both synthetic creation of data with a boosting-based parameter adjustments, whereas LuminoFeat is constructed to optimized the valuable features from the dataset by dynamically adjusting the threshold of the features and discarding redundancies and also with the selection of customized machine learning classifiers. Altogether, the proposed model improves the computational cost, accuracy, and interpretation significantly when compared to conventional approaches. The concise evaluation metrics performance using multiple classifiers highlight the model robustness, with Bagging classifier obtaining performance score; accuracy of 99.43%, precision of 99.36%, recall of 99.52%, F1-score of 99.34%, Specificity of 99.34%, ROC-AUC of 99.57% and PR AUC of 99.65%. This paper demonstrates the robustness of the proposed SynoBoost-LuminoFeatML model in resolving financial fraud transaction issues in real-word settings.
References
- A. Almazroi and N. Ayub, “Online Payment Fraud Detection Model Using Machine Learning Techniques,” in IEEE Access, vol. 11, 2023, doi: 10.1109/ACCESS.2023.3339226
- S. Bhakta, S. Ghosh and B. Sadhukhan, “Credit Card Fraud Detection Using Machine Learning: A Comparative Study of Ensemble Learning Algorithms,” 2023 9th International Conference on Smart Computing and Communications (ICSCC), Kochi, Kerala, India, 2023, pp. 296-301, doi: 10.1109/ICSCC59169.2023.10335075.
- Xiuguo and D. Shengyong, “An Analysis on Financial Statement Fraud Detection for Chinese Listed Companies Using Deep Learning,” in IEEE Access, vol. 10, 2022.
- Patel, M. Pandey and R. D, “Fraud Detection in Financial Transactions: A Machine Learning Approach,” 2024 Ninth International Conference on Science Technology Engineering and Mathematics (ICONSTEM), Chennai, India, 2024, pp. 1-8, doi: 10.1109/ICONSTEM60960.2024.10568903.
- Abdallah, A., Maarof, M. A., & Zainal, A. (2016). Fraud detection system: A survey. Journal of Network and Computer Applications, 68, 90-113.
- Frank, E., & Oluwaseyi, J. (2024). Challenges and limitations of fraud detection in NoSQL database systems.
- Hilal, W., Gadsden, S. A., & Yawney, J. (2022). Financial fraud: a review of anomaly detection techniques and recent advances. Expert systems With applications, 193, 116429.
- Bello, O. A., & Olufemi, K. (2024). Artificial intelligence in fraud prevention: Exploring techniques and applications challenges and opportunities. Computer Science & IT Research Journal, 5(6), 1505-1520.
- Bello, O. A., Ogundipe, A., Mohammed, D., Adebola, F., & Alonge, O. A. (2023). AI-Driven Approaches for Real-Time Fraud Detection in US Financial Transactions: Challenges and Opportunities. European Journal of Computer Science and Information Technology, 11(6), 84-102.
- Bao, Y., Hilary, G., & Ke, B. (2022). Artificial intelligence and fraud detection. Innovative Technology at the Interface of Finance and Operations: Volume I, 223-247.
- Al‐dahasi, E. M., Alsheikh, R. K., Khan, F. A., & Jeon, G. (2024). Optimizing fraud detection in financial transactions with machine learning and imbalance mitigation. Expert Systems, e13682.
- Kaur, H., Pannu, H. S., & Malhi, A. K. (2019). A systematic review on imbalanced data challenges in machine learning: Applications and solutions. ACM computing surveys (CSUR), 52(4), 1-36.
Download all article in PDF
