Representation Learning on Graphs to Identifying Circular Trading in Goods and Services Tax

TL;DR

This paper proposes a graph representation learning framework using big data analytics to detect communities of circular traders involved in GST tax evasion, demonstrated on real-life Indian tax data.

Contribution

It introduces a novel graph-based approach leveraging representation learning to identify illegal circular trading communities in large GST datasets.

Findings

Uncovered multiple circular trading communities in real GST data.

Demonstrated effectiveness of graph learning techniques in tax evasion detection.

Provided a scalable framework for authorities to identify illicit trading networks.

Abstract

Circular trading is a form of tax evasion in Goods and Services Tax where a group of fraudulent taxpayers (traders) aims to mask illegal transactions by superimposing several fictitious transactions (where no value is added to the goods or service) among themselves in a short period. Due to the vast database of taxpayers, it is infeasible for authorities to manually identify groups of circular traders and the illegitimate transactions they are involved in. This work uses big data analytics and graph representation learning techniques to propose a framework to identify communities of circular traders and isolate the illegitimate transactions in the respective communities. Our approach is tested on real-life data provided by the Department of Commercial Taxes, Government of Telangana, India, where we uncovered several communities of circular traders.