The findings provide valuable insights into the banking sector’s dynamic fraud detection landscape.
Authors
Hanna Olasiuk, Associate Professor, Jindal Global Business School, O.P. Jindal Global University, Sonipat, Haryana, India.
Sudhanshu Singh, School of Business, Galgotias University, Gautam Buddh Nagar, Uttar Pradesh, India.
Tetiana Ganushchak, Economic and Finance Enterprise Department, State University of Trade and Economics, Kyiv, Ukraine.
Summary
Fraud detection in banking is crucial for averting losses, preserving client confidence, and ensuring regulatory compliance. This study employs a machine learning text-mining technique named structural topic modelling to explore a dataset comprising 331 articles from Elsevier’s Scopus database, covering 2003 to 2022.
It concentrates on fraud detection within the banking sector, investigating publication patterns, emphasising influential countries, and identifying significant sources. India emerges as a substantial contributor, with 54 articles, mainly in single-country publications (47 articles) and a multiple-country publication Ratio of 0.13. “Advances in Intelligent Systems and Computing” notably contributes 14 articles.
Structural topic modelling reveals four distinct thematic clusters: Machine learning in fraud detection, Banking transaction fraud detection, Customer behaviour in fraud detection, and Credit card transaction fraud detection. The findings provide valuable insights into the banking sector’s dynamic fraud detection landscape. These thematic clusters enhance our understanding of this field, aiding researchers seeking to publish their work in reputable sources. These findings hold significant implications for a wide range of stakeholders, encompassing academics, practitioners, regulators, and policymakers.
Published in: 2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)
To read the full article, please click here.
