Fraud Detection Using Neural Networks: A Case Study of Income Tax

Belle Fille Murorunkwere, Origene Tuyishimire, Dominique Haughton and Joseph Nzabanita
Additional contact information
Belle Fille Murorunkwere: African Center of Excellence in Data Science, University of Rwanda, KK 737 Street, Gikondo, Kigali P.O. Box 4285, Rwanda
Origene Tuyishimire: African Institute for Mathematical Sciences, KN 3 Street, Remera, Kigali P.O. Box 7150, Rwanda
Dominique Haughton: Department of Mathematical Sciences and Global Studies, Bentley University, Watham, MA 02452-4705, USA
Joseph Nzabanita: Department of Mathematics, College of Science and Technology, University of Rwanda, KN 67 Street, Nyarugenge, Kigali P.O. Box 3900, Rwanda

Future Internet, 2022, vol. 14, issue 6, 1-14

Abstract: 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.

Keywords: fraud detection; income tax; multi-layer perceptron; neural network; tax fraud (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed

Downloads: (external link)
https://www.mdpi.com/1999-5903/14/6/168/pdf (application/pdf)
https://www.mdpi.com/1999-5903/14/6/168/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:14:y:2022:i:6:p:168-:d:828622

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().