Search Results (2)

Detecting tax fraud is a top objective for practically all tax agencies in order to maximize revenues and maintain a high level of compliance. Data mining, machine learning, and other approaches such as traditional random auditing have been used in many studies to deal with tax fraud. The goal of this study is to use Artificial Neural Networks to identify factors of tax fraud in income tax data. The results show that Artificial Neural Networks perform well in identifying tax fraud with an accuracy of 92%, a precision of 85%, a recall score of 99%, and an AUC-ROC of 95%. All businesses, either cross-border or domestic, the period of the business, small businesses, and corporate businesses, are among the factors identified by the model to be more relevant to income tax fraud detection. This study is consistent with the previous closely related work in terms of features related to tax fraud where it covered all tax types together using different machine learning models. To the best of our knowledge, this study is the first to use Artificial Neural Networks to detect income tax fraud in Rwanda by comparing different parameters such as layers, batch size, and epochs and choosing the optimal ones that give better accuracy than others. For this study, a simple model with no hidden layers, softsign activation function performs better. The evidence from this study will help auditors in understanding the factors that contribute to income tax fraud which will reduce the audit time and cost, as well as recover money foregone in income tax fraud. Full article

This article analyses how the monies generated for, and from, corporate financial crimes are controlled, concealed, and converted through the use of organisational structures in the form of otherwise legitimate corporate entities and arrangements that serve as vehicles for the management of illicit finances. Unlike the illicit markets and associated ‘organised crime groups’ and ‘criminal enterprises’ that are the normal focus of money laundering studies, corporate financial crimes involve ostensibly legitimate businesses operating within licit, transnational markets. Within these scenarios, we see corporations as primary offenders, as agents, and as facilitators of the administration of illicit finances. In all cases, organisational structures provide opportunities for managing illicit finances that individuals alone cannot access, but which require some element of third-party collaboration. In this article, we draw on data generated from our Partnership for Conflict, Crime, and Security Research (PaCCS)-funded project on the misuse of corporate structures and entities to manage illicit finances to make a methodological and substantive addition to the literature in this area. We analyse two cases from our research—corporate bribery in international business and corporate tax fraud—before discussing three main findings: (1) the ostensible legitimacy created through abuse of otherwise lawful business arrangements; (2) the effective anonymity and insulation afforded through such misuse; and (3) the necessity for facilitation by third-party professionals operating within a stratified market. The analysis improves our understanding of how and why business offenders misuse what are otherwise legitimate business structures, arrangements, and practices in their criminal enterprise. Full article