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{196477,
        author = {Jeet Bandyopadhyay and Disha Roy and Roshni Ghosh Tagore and Hrishav Hari and Mahendrani Chanda},
        title = {Behavioural-Aware Hybrid Ensemble Model with Cost-Sensitive and Explainable Credit Card Fraud Detection using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {4111-4119},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196477},
        abstract = {With a rise in digital transactions, credit card fraudulence is an issue of growing concern. Correctly detecting fraud transactions is hard due to data imbalance, the dynamic nature of fraud patterns, and the low interpretability of existing models. To increase the accuracy on fraud detection, the proposed model introduced a Behavioural-Aware Hybrid Ensemble Model that takes both supervised and unsupervised machine learning benefits into account. The proposed model is optimal in terms of high performance and practical value by extracting behavioural features including transaction time, frequency, and location and by employing cost-sensitive learning and model explainability with SHAP. Our approach makes use of Random Forest, XGBoost, and Logistic Regression as supervised classifiers and Autoencoder and Isolation Forest as an unsupervised anomaly detection technique. To deal with data imbalance, the model is trained using SMOTE, and it is assessed using real-world metrics such as cost, recall, and AUC-ROC.},
        keywords = {Credit Card Fraud Detection, Hybrid Ensemble model, Cost Sensitive-learning, SMOTE, Autoencoder, Explainable AI (XAI) using SHAP},
        month = {April},
        }