Link prediction techniques to handle tax evasion

Mathews, Jithin and Mehta, Priya and Suryamukhi, K. and Babu, Sobhan (2020) Link prediction techniques to handle tax evasion. In: 3rd ACM India Joint International Conference on Data Science and Management of Data, CODS-COMAD 2021, 2-4 January 2021, Virtual, Online.

	Text Link_prediction_techniques.pdf - Published Version Available under License Creative Commons Attribution. Download (861kB)
	Text Link_prediction_techniques.pdf Available under License Creative Commons Attribution. Download (861kB)

Abstract

Circular trading of goods is a carefully designed scam ubiquitous among fraudulent business dealers all around the world. Dealers involved in this scheme create an artificial trading network by issuing doctored sales-invoices amongst themselves without any movement of goods. In practice, it is observed that almost all cases of circular trade involve two or three dealers. Here, we work towards predicting circular trade involving three dealers. For the same, we built four different classification models consisting of feature variables tailored for predicting any plausible circular trade amongst three dealers. In particular, the logistic regression model gave the best performance among all the four different models with a prediction accuracy of 80%. Interestingly, we observe that a feature variable formed by using the personalised PageRank technique significantly improves the model over the state of the art link prediction variables. Predicting a future circular trade from a huge network of sales-transactions data is of significant importance to the tax enforcement officers. In addition to automating the process of detecting circular trading, which is manually impossible, this model helps them to target on a set of plausible evaders and take appropriate preventive measures. This model have been developed for the Commercial Taxes Department, Government of Telangana, India, using their first two quarter's tax returns dataset. © 2021 ACM.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Babu, Sobhan	UNSPECIFIED

Item Type:

Conference or Workshop Item (Paper)

Additional Information:

We are very grateful to the Telangana state government, India, for sharing the commercial tax dataset, which is used in this work. This work has been supported by Visvesvaraya PhD Scheme for Electronics and IT, Media Lab Asia, grant number EE/2015-16/023/MLB/ MZAK/0176.

Uncontrolled Keywords:

circular trading; forensic accounting; goods and services tax; link prediction; logistic regression; PageRank algorithm; tax evasion

Subjects:

Computer science

Divisions:

Department of Computer Science & Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

23 Nov 2022 09:46

Last Modified:

23 Nov 2022 09:46