The Psychological Analysis for Early Detection of Accounting Fraud: A Psychological Methodolog

Abstract

Abstract
Financial accounting fraud detection (FAFD) has emerged as a hot issue in academia, research, and business due to the present economic climate's increase in financial accounting fraud. As a result of the organization's internal auditing system's inability to detect accounting fraud, forensic accounting processes have been implemented. Forensic accounting has a difficult time coping with the volume and complexity of financial data, which is why data mining tools are becoming increasingly important. For the first time, a full literature analysis is provided on the use of data mining tools to identify instances of financial accounting fraud, and an approach to detecting such instances is proposed. Financial accounting fraud detection strategies may benefit from the systematic and extensive literature study of data mining techniques. According to the conclusions of this research, data mining techniques such as logistic models, neural networks, Bayesian belief networks, and decision trees have been used most extensively to give fundamental answers to the challenges inherent in the identification and classification of fraudulent data.