Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189019,
        author = {Mohammed Saniya and Arif Mohammad Abdul},
        title = {Fraud Detection in Banking Data By Machine Learning Technique},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {4455-4458},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189019},
        abstract = {Real-time fraud detection is crucial for financial institutions because of the sharp increase in fraudulent activity brought about by the quick growth of digital banking and internet transactions. However, there are significant obstacles due to the very unbalanced structure of fraud datasets and the constantly changing fraud patterns. This paper suggests an enhanced fraud detection approach that combines sophisticated ensemble machine learning methods, Bayesian hyperparameter optimization, and class weight-tuning. A majority-voting approach is used to merge LightGBM, XGBoost, and CatBoost models, and deep learning is used to further optimize weight-tuning hyperparameters for unbalanced data.Significant performance gains are seen in experiments using real-world banking data. The suggested approach confirms its resilience despite severe class imbalance by achieving recall improvements of up to 12%, precision improvements of up to 97%, F1-scores above 95%, and MCC values considerably higher than baseline models. When compared to state-of-the-art methods, the optimized framework shows better detection capability, and ensemble combinations like LG+XG+CAT outperform individual models. These findings demonstrate that the suggested hybrid, weight-tuned ensemble technique offers a very successful method for detecting banking fraud in the real world.},
        keywords = {Fraud detection using credit cards, Machine Learning Frameworks, Predictive Fraud Systems Deep Learning Enhancement},
        month = {December},
        }