Review article
https://doi.org/10.32985/ijeces.14.2.12
Review of Loan Fraud Detection Process in the Banking Sector Using Data Mining Techniques
Fahd Sabry Esmail
; Helwan University, Faculty of Commerce & Business Administration, Department of Business Information Systems Cairo, Egypt
Fahad Kamal Alsheref
; Beni-Suef University, Faculty of Computers and Artificial Intelligence, Department of Information Systems Beni-Suef, Egypt
Amal Elsayed Aboutabl
orcid.org/0000-0002-7189-9274
; Helwan University, Faculty of Computers and Artificial Intelligence, Department of Computer Science Cairo, Egypt
Abstract
At the era of digital transformation, fraud has dramatically increased, notably in the banking industry. Annually, it now costs the world's economies billions of dollars. Daily, news of financial fraud has a negative influence on the world economy. According to the harsh loss caused by fraud, effective strategies and methods for avoiding income statement fraud have to be implemented. Also, the procedure of identification should be applied. This is regarded as a result of the development of modern technology, modern invention, and the rapidity of global communications. Actually, deterrent technologies are most effective to reduce fraud and overcome cons. So, it is necessary to find ways to overcome such deterrence by depending on developed methods to identify fraud. Data mining techniques are currently the most widely used methods for the prevention and detection of financial fraud. The use of datasets for fraud detection complies with the norms of data mining, which include feature selection, representation, data gathering and management, pre-processing, comment, and summative evaluation. Methodologies for identifying fraud are essential if we want to catch criminals after fraud prevention has failed. The greatest fraud detection strategies for locating loan banking and financial fraud are compared in this article.
Keywords
Fraud; Loan Fraud; Loan Fraud detection; Data mining techniques.;
Hrčak ID:
294592
URI
Publication date:
27.2.2023.
Visits: 2.137 *