Abstract
The goal of the present research is to contribute to the detection of tax fraud concerning personal income tax returns (IRPF, in Spanish) filed in Spain, through the use of Machine Learning advanced predictive tools, by applying Multilayer Perceptron neural network (MLP) models. The possibilities springing from these techniques have been applied to a broad range of personal income return data supplied by the Institute of Fiscal Studies (IEF). The use of the neural networks enabled taxpayer segmentation as well as calculation of the probability concerning an individual taxpayer’s propensity to attempt to evade taxes. The results showed that the selected model has an efficiency rate of 84.3%, implying an improvement in relation to other models utilized in tax fraud detection. The proposal can be generalized to quantify an individual’s propensity to commit fraud with regards to other kinds of taxes. These models will support tax offices to help them arrive at the best decisions regarding action plans to combat tax fraud.
Highlights
The quantification and detection of tax fraud is a top priority amongst the most important goals of tax offices in several countries
In view of the significance of the problems resulting from tax fraud, and bearing in mind efficiency, equity, and the capacity to procure money, it is evident that improving the efficacy of measures to reduce tax fraud is high on the list of tax offices priorities
This paper attempts to make a contribution through research conducted on the application of Neural Network models to income tax returns samples provided by the Spanish Institute of Fiscal Studies, with a view to facilitating the detection of taxpayers who evade tax by quantifying an individual taxpayer’s tendency to commit fraud
Summary
The quantification and detection of tax fraud is a top priority amongst the most important goals of tax offices in several countries. This paper attempts to make a contribution through research conducted on the application of Neural Network models to income tax returns samples provided by the Spanish Institute of Fiscal Studies, with a view to facilitating the detection of taxpayers who evade tax by quantifying an individual taxpayer’s tendency to commit fraud. With this goal in mind, use was made of Machine Learning advanced predictive tools for supervised learning, of the neural networks model. The last section consists of a brief conclusion, in addition to detailing future research possibilities arising from the results obtained
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
