Prediction of Bank Transaction Fraud Using TabNet—an Adaptive Deep Learning Architecture

B.S. Prashanth; Manoj Kumar; Ariful Hoque; Nasser Al Muraqab; Immanuel Azaad Moonesar; Udo Christian Braendle; Ananth Rao

doi:10.1016/j.iref.2026.104916

Back

Prediction of Bank Transaction Fraud Using TabNet—an Adaptive Deep Learning Architecture

Journal article

Open access

Peer reviewed

Prediction of Bank Transaction Fraud Using TabNet—an Adaptive Deep Learning Architecture

B.S. Prashanth, Manoj Kumar, Ariful Hoque, Nasser Al Muraqab, Immanuel Azaad Moonesar, Udo Christian Braendle and Ananth Rao

International review of economics & finance, Vol.106, 104916

2026

DOI: https://doi.org/10.1016/j.iref.2026.104916

Files and links (1)

pdf

Published5.46 MBDownload View

CC BY-NC-ND V4.0, Open Access

Abstract

Alternative deep neural networks (DNNs)

Decision support systems

Digital banking fraud

Explainable artificial intelligence (XAI)

FinTech

Sustainable Development Goals 8 and 16

TabNet

The development of online banking has brought about an increase in fraudulent operations, which is a major problem for banks. This study delves into the urgent requirement for interpretable, scalable, and top-notch fraud detection systems by using TabNet, an adaptable deep learning framework, on a Kaggle dataset consisting of actual bank transactions in India. Maximizing operational risk management by improving the accuracy of transaction anomaly detection and ensuring regulatory compliance through transparent models is the goal. We utilize a supervised learning pipeline that incorporates the Synthetic Minority Over-sampling Technique (SMOTE) to ensure that classes are balanced. Subsequently, we conduct thorough exploratory data analysis (EDA) to identify patterns of fraud, both during specific times and across behaviors. On this dataset, five different deep learning architectures are tested: DNN, GRU, LSTM, CNN1D, and TabNet. Assessment of predictive performance was carried out using a 3-fold cross-validation framework. With a ROC-AUC of 0.9739 and an accuracy of 97.39%, TabNet considerably outperformed the competition. The method of sparse feature selection used improved interpretability, generalized better on tabular data, and produced fewer false positives and negatives. Critical insights for operational fraud detection systems and a contribution to the broader literature on explainable AI (XAI) in financial decision-making are offered by the findings. Goals 8 and 16 of the Sustainable Development Agenda are supported by this study, which promotes inclusive economic growth and institutional transparency. Supporting strong, policy-compliant, and interpretable decision-support systems, it also offers practical use for real-time implementation in banking infrastructure.

Details

Title: Prediction of Bank Transaction Fraud Using TabNet—an Adaptive Deep Learning Architecture
Authors/Creators: B.S. Prashanth - Department of Information Science and Engineering, Nitte Meenakshi Institute of Technology, Bengaluru, India
Manoj Kumar - Department of Information Science and Engineering, Nitte Meenakshi Institute of Technology, Bengaluru, India
Ariful Hoque - Murdoch University, College of Business
Nasser Al Muraqab - University of Dubai
Immanuel Azaad Moonesar - Mohammed Bin Rashid School of Government
Udo Christian Braendle - IMC University of Applied Sciences Krems
Ananth Rao - Mohammed Bin Rashid School of Government
Publication Details: International review of economics & finance, Vol.106, 104916
Publisher: Elsevier Inc.
Identifiers: 991005852586507891
Murdoch Affiliation: Murdoch University; College of Business
Language: English
Resource Type: Journal article

Metrics

4 Record Views