Enhancement to Training of Bidirectional GAN : An Approach to Demystify Tax Fraud

TL;DR

This paper introduces a novel training approach for bidirectional GANs to improve outlier detection, specifically targeting tax fraud identification by analyzing correlation and ratio parameters from tax data.

Contribution

The paper proposes a new training method for BiGANs that enhances outlier detection capabilities in complex, high-dimensional datasets like tax return data.

Findings

Effective detection of tax return manipulators using cosine similarity measures.

Successful application of the method on real taxpayer data from Telangana, India.

Demonstrated improved outlier detection performance over existing techniques.

Abstract

Outlier detection is a challenging activity. Several machine learning techniques are proposed in the literature for outlier detection. In this article, we propose a new training approach for bidirectional GAN (BiGAN) to detect outliers. To validate the proposed approach, we train a BiGAN with the proposed training approach to detect taxpayers, who are manipulating their tax returns. For each taxpayer, we derive six correlation parameters and three ratio parameters from tax returns submitted by him/her. We train a BiGAN with the proposed training approach on this nine-dimensional derived ground-truth data set. Next, we generate the latent representation of this data set using the $encoder$ (encode this data set using the $encoder$) and regenerate this data set using the $generator$ (decode back using the $generator$) by giving this latent representation as the input. For each taxpayer, compute the cosine similarity between his/her ground-truth data and regenerated data. Taxpayers with lower cosine similarity measures are potential return manipulators. We applied our method to analyze the iron and steel taxpayers data set provided by the Commercial Taxes Department, Government of Telangana, India.