At present, the biggest concern of every organization is to detect and control financial fraud. Tax frauds cause the loss of billions of dollars every year. As a result, data mining techniques are used to combat the growing problem of tax fraud. Tax evasions cause a reduction in revenue collection. It also has a bleak impact on government policies and budget. The goal of this study is to describe the use of data analytics tools to process and analyze tax data related to value-added tax evasions. This study is a conceptual perspective that provides a theoretical and methodological basis for data analytic application to detect evasions in taxation. This study will also explain that tax collecting companies can identify fraud detection through these methods and can save a lot of time and finances. Outlier analysis is applied to a wide variety of fields which include fraud detection, medical diagnosis, intrusion recognition, web analytics and fault identification. This project aims to detect tax fraud by using data analytics technique as the outlier analysis. In this project, an outlier detection technique used for identifying tax fraud, especially in VAT. Research on financial fraud detection has a long tradition. Recent theoretical developments have revealed that the clustering technique used for outlier detection is not only on point but also very cheap and helpful.
Professional Studies (MS)
Department, Program, or Center
Graduate Programs & Research (Dubai)
Karmustaji, Ayesha, "Fraud Detection using Data Analytics" (2021). Thesis. Rochester Institute of Technology. Accessed from