International Journal of Information Engineering and Electronic Business (IJIEEB)
IJIEEB Vol. 18, No. 5, 8 Oct. 2026
Cover page and Table of Contents: PDF (size: 1002KB)
Multi-class Financial Payment Fraud Detection via a CNN-CfC Hybrid Architecture with Explainable Feature Engineering
PDF (1002KB), PP.27-44
Views: 0 Downloads: 0
Author(s)
Index Terms
Financial Fraud Detection, Hybrid Deep Learning, Multiclass Classification, Feature Engineering, Explainable AI, Scalability, SHAP.
Abstract
With the growing digitization of financial services, fraudulent activities in online transactions are becoming increasingly sophisticated and widespread. An automated and intelligent financial transaction fraud detection system is necessary to properly detect and categorize fraudulent incidents in order to address this challenge. The majority of previous research has been on using binary classification to identify fraudulent transactions. Previous efforts were often hindered by class imbalance, inadequate feature selection, suboptimal prediction accuracy, and insufficient hyperparameter tuning. This paper suggests a hybrid deep learning framework for multi-class financial fraud detection that combines Convolutional Neural Network (CNN) and Closed-form Continuous-time (CfC) models in order to handle these problems. By analyzing transactional and behavioral characteristics, the model is intended to categorize fraud situations into distinct groups, including Phishing, Account Takeover (ATO), Card Skimming, and No Fraud. The proposed CfC-CNN model was not only trained but also tested on a large transaction augmented dataset that was enhanced with contextual characteristics. This work uses the IBM financial fraud dataset and considers 5 million transactions. This work investigated four classes such as phishing, ATO, card skimming, and no fraud. Label encoding was used as a preprocessing method for the contextual and category information. The dataset was refined for best performance by feature selection using Chi-Square and the random search method for hyper parameter tweaking. The proposed CfC-CNN model achieved at least .03 percent accuracy gain and .49 percent F1 score gain over the compared previous works.
Cite This Paper
Maeidah Rahman Jafrin, Mahfuzul Hoq Chowdhury, "Multi-class Financial Payment Fraud Detection via a CNN-CfC Hybrid Architecture with Explainable Feature Engineering", International Journal of Information Engineering and Electronic Business(IJIEEB), Vol.18, No.5, pp. 27-44, 2026. DOI:10.5815/ijieeb.2026.05.03
Reference
[1]Z. Shen et al., "Research on Application of Whale Optimization Algorithm in Financial Payment Fraud Detection," 2025 4th International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID), Guangzhou, China, 2025, pp. 47-50, doi: 10.1109/ICAID65275.2025.11034613.
[2]H. K. Kwon et al., “Recent transformation of the U.S. economy,” Springer Books, In: Openness and Coordination, Chapter 0, Springer, Singapore, pp. 79-117, DOI: 10.1007/978-981-97-3352-1_4.
[3]A. Rehman et al., “Impact of Fraud Risk Assessment on Good Corporate Governance: Case of Public Listed Companies in Oman,” Business Systems Research Journal, vol. 11, no. 1, pp. 16–30, Mar. 2020.
[4]B. Gogoi et al., "Phishing and Fraudulent Email Detection through Transfer Learning using pretrained transformer models," 2022 IEEE 19th India Council International Conference (INDICON), Kochi, India, 2022, pp. 1-6, doi: 10.1109/INDICON56171.2022.10040097.
[5]R. Santoso et al., "Detecting Account Takeover (ATO) in Fintech Companies Using Machine Learning," 2024 6th International Conference on Cybernetics and Intelligent System (ICORIS), Surakarta, Indonesia, 2024, pp. 1-6, doi: 10.1109/ICORIS63540.2024.10903690.
[6]S. I. Goudar et al., "Intelligent Fraud Detection Techniques in Credit Card and Internet Banking," 2024 International Conference on Communication, Control, and Intelligent Systems (CCIS), Mathura, India, 2024, pp. 1-6, doi: 10.1109/CCIS63231.2024.10932113.
[7]J. K. Afriyie et al., “A supervised machine learning algorithm for detecting and predicting fraud in credit card transactions,” Decision Analytics Journal, vol. 6, no. 1, pp. 1–10, Jan. 2023.
[8]E. Ileberi et al., “A machine learning based credit card fraud detection using the GA algorithm for feature selection, ” Journal Of Big Data, vol. 9, no. 1, Feb. 2022, pp. 1–15.
[9]Kaggle, “Credit card fraud detection,” https://www.kaggle.com/datasets/mlg-ulb/creditcardfraud, accessed on June 2024.
[10]D. Almhaithawi et al., “Example-dependent cost-sensitive credit cards fraud detection using SMOTE and Bayes minimum risk,” SN Applied Sciences, Springer, vol. 2, no. 9, 2020, pp. 1–13.
[11]A. S. Hussein et al., “Credit Card Fraud Detection Using Fuzzy Rough Nearest Neighbor and Sequential Minimal Optimization with Logistic Regression, ” International Journal of Interactive Mobile Technologies (iJIM), vol. 15, no. 05, pp. 24– 41, 2021.
[12]A. Ukwu et al., “Financial Fraud Detection Using Machine Learning Models,” 2025 18th International Conference on Development in eSystem Engineering (DeSE), Bucharest, Romania, 2025, pp. 435-439.
[13]Philomina M et al., "Smart Detection of Credit Card Fraud Using Deep Learning Technique," 2025 6th International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India, 2025, pp. 1471-1474.
[14]V. Rishitha et al., "UPI Fraud Detection Using Convolutional Neural Networks," 2026 IEEE 18th International Conference on Computational Intelligence and Communication Networks (CICN), Manila, Philippines, 2026, pp. 828-834.
[15]S. Islam et al., "Real-Time Credit Card Fraud Detection Using Graph Attention Networks with Cost-Sensitive Learning," 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking(QPAIN), Chittagong, Bangladesh, 2026, pp. 1-6.
[16]Y. Alghofaili et al., “A financial fraud detection model based on LSTM deep learning technique, ” Journal of Applied Security Research, vol. 15, no. 4, pp. 498–516, 2020.
[17]O. Ola et al., “Enhanced credit card fraud detection using deep learning techniques, ” Journal of Cybersecurity and Information Management, vol. 14, no. 2, pp. 323–333, 2024.
[18]Kaggle, “IEEE-CIS fraud detection,” https://www.kaggle.com/competitions/ieee-fraud-detection/, accessed on July 2025.
[19]F. K. Alarfaj et al., “Credit card fraud detection using state-of-the-art machine learning and deep learning algorithms, ” IEEE Access, vol. 10, no. 1, pp. 39 700–39 715, 2022.
[20]F. A. Nama et al., “Financial fraud identification using deep learning techniques, ” Al-Salam Journal for Engineering and Technology, vol. 3, no. 1, pp. 141–147, 2024.
[21]E. F. Malik et al., “Credit card fraud detection using a new hybrid machine learning architecture, ” Mathematics, MDPI, vol. 10, no. 9, pp. 1-16, 2022.
[22]E. Esenogho et al., “A neural network ensemble with feature engineering for improved credit card fraud detection, ” in IEEE Access, vol. 10, pp. 16 400–16 407, 2022.
[23]S. N. Kalid et al., “A multiple classifiers system for anomaly detection in credit card data with unbalanced and overlapped classes,” IEEE Access, vol. 8, no. 1, pp. 28 210–28 221, 2020.
[24]N. B. R. Reddy et al., “Fraud Transaction Detection Approach using Machine Learning Hybrid techniques, ” International Journal of Scientific Research in Science and Technology, vol. 10, no. 2, pp. 90–96, 2023.
[25]Kaggle, “Synthetic Financial Datasets For Fraud Detection,” https://www.kaggle.com/datasets/ealaxi/paysim1, accessed on July 2025.
[26]E. Ileberi et al., “Performance evaluation of machine learning methods for credit card fraud detection using smote and adaboost,” IEEE Access, vol. 9, no. 1, pp. 165 286–165 294, 2021.
[27]N. Adesina et al., “Credit card fraud Detection,” International Journal of Science and Research Archive, vol. 12, no. 2, pp. 2072– 2080, 2024.
[28]D. Rzayeva et al., “A combination of deep neural networks and K-Nearest neighbors for credit card fraud detection,” arXiv preprint, https://doi.org/10.48550/arXiv.2205.15300, 2022, pp. 1–6.
[29]M. E. Lokanan et al., “Predicting mobile money transaction fraud using machine learning algorithms,” Applied AI Letters, vol. 4, no. 2, https://doi.org/10.1002/ail2.85, 2023, pp. 1–15.
[30]H. Du et al., “AutoEncoder and LightGBM for credit card fraud detection problems,” Symmetry Journal, MDPI, vol. 15, no. 4, 2023, pp. 1-16.
[31]S. Farag et al., “Data and model centric approaches for card fraud detection,” 2023 International Conference on Computer and Applications (ICCA), Cairo, Egypt, 2023, pp. 1-6.
[32]Kaggle, “IBM Credit Card Fraud Detection: EDA+Random Forest,” https://www.kaggle.com/code/yichenzhang1226/ibm-credit-card-fraud-detection-eda-random-foresty,last accessed on June, 2025.
[33]Kaggle, “Credit Card Transactions Fraud Detection Dataset,” https://www.kaggle.com/datasets/kartik2112/fraud-detection, last accessed on June, 2025.
[34]H. Tingfei et al., “Using variational auto encoding in credit card fraud detection,” IEEE Access, vol. 8, no. 1, pp. 149 841–149 853, Jan. 2020, doi: 10.1109/ACCESS.2020.3015600.
[35]I. Padhi et al., “Tabular transformers for modeling multivariate time series,” 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada, 2021, pp. 3565-3569, doi: 10.1109/ICASSP39728.2021.9414142.
[36]I. D. Mienye et al., “A Hybrid Deep Learning Approach with Generative Adversarial Network for Credit Card Fraud Detection,” Technologies, vol. 12, no. 10, pp. 1-12, 2024, https://doi.org/10.3390/technologies12100186.
[37]Y. Ding et al., “Credit card fraud detection based on improved variational autoencoder generative adversarial network,” IEEE Access, vol. 11, no. 1, pp. 83 680–83 691, 2023.
[38]R. Hasani et al., “Closed-form continuous-time neural networks,” Nature Machine Intelligence, vol. 4, no. 11, pp. 992–1003, Nov. 2022.