A Novel Example-Dependent Cost-Sensitive Stacking Classifier to Identify Tax Return Defaulters





goods and services tax, tax evasion, xample-dependent cost-sensitive stacking classifier, example-dependent cost-sensitive ANNs, Benford’s analysis, social network analysis, cosine similarity


Tax evasion refers to an entity indulging in illegal activities to avoid paying their actual tax liability. A tax return statement is a periodic report comprising information about income, expenditure, etc. One of the most basic tax evasion methods is failing to file tax returns or delay filing tax return statements. The taxpayers who do not file their returns, or fail to do so within the stipulated period are called tax return defaulters. As a result, the Government has to bear the financial losses due to a taxpayer defaulting, which varies for each taxpayer. Therefore, while designing any statistical model to predict potential return defaulters, we have to consider the real financial loss associated with the misclassification of each individual. This paper proposes a framework for an example-dependent cost-sensitive stacking classifier that uses cost-insensitive classifiers as base generalizers to make predictions on the input space. These predictions are used to train an example-dependent cost-sensitive meta generalizer. Based on the meta-generalizer choice, we propose four variant models used to predict potential return defaulters for the upcoming tax-filing period. These models have been developed for the Commercial Taxes Department, Government of Telangana, India. Applying our proposed variant models to GST data, we observe a significant increase in savings compared to conventional classifiers. Additionally, we develop an empirical study showing that our approach is more adept at identifying potential tax return defaulters than existing example-dependent cost-sensitive classification algorithms.



Download data is not yet available.


S. Dani, “A research paper on an impact of goods and service tax (gst) on indian economy,” Business and Economics Journal, vol. 07, Jan. 2016. DOI: 10.4172/2151-6219. 1000264.

J. Lismont, E. Cardinaels, L. Bruynseels, S. D. Groote, W. Lemahieu, and J. Vanthienen, “Predicting tax avoidance by means of social network analytics,” Decision Support Systems, vol. 108, pp. 13–24, 2018.

P. A. Bianchi and M. Minutti-Meza, “Professional networks and client tax avoidance: Evidence from the italian statutory audit regime,” SSRN Electronic Journal, Jan. 2016. DOI: 10.2139/ssrn.2601570.

V. V. Vlasselaer, L. Akoglu, T. Eliassi-Rad, M. Snoeck, and B. Baesens, “Guilt-by-constellation: Fraud detection by suspicious clique memberships,” in 2015 48th Hawaii International Conference on System Sciences, 2015, pp. 918–927.

Y. Sahin and E. Duman, “Detecting credit card fraud by ann and logistic regression,” in 2011 International Symposium on Innovations in Intelligent Systems and Applications, 2011, pp. 315–319.

C. Ling and V. Sheng, “Cost-sensitive learning and the class imbalance problem,” Encyclopedia of Machine Learning, Jan. 2010.

A. C. Bahnsen, D. Aouada, and B. Ottersten, “Example-dependent cost-sensitive logistic regression for credit scoring,” in 2014 13th International Conference on Machine Learning and Applications, 2014, pp. 263–269.

A. C. Bahnsen, D. Aouada, and B. Ottersten, Ensemble of example-dependent costsensitive decision trees, 2015. arXiv: 1505.04637 [cs.LG].

D. Wolpert, “Stacked generalization,” Neural Networks, vol. 5, pp. 241–259, Dec. 1992. DOI: 10.1016/S0893-6080(05)80023-1.

M. Kukar and I. Kononenko, “Cost-sensitive learning with neural networks,” in Proceedings of the 13th European Conference on Artificial Intelligence (ECAI-98, John Wiley & Sons, 1998, pp. 445–449.

M. L. J. Nigrini Mark J., “The Use of Benford’s Law as an Aid in Analytical Procedures,” Auditing: A journal of practice & theory, vol. 41, p. 52, 1997.

A. Asllani and M. Naco, “Using Benford¡¯s Law for Fraud Detection in Accounting Practices,” Journal of Social Science Studies, vol. 2, no. 1, pp. 129–143, Jan. 2015. [Online]. Available: https://ideas.repec.org/a/mth/jsss88/v2y2015i1p129-143.html.

C. Durtschi, W. Hillison, and C. Pacini, “The effective use of benford’s law to assist in detecting fraud in accounting data,” J. Forensic Account, vol. 5, Jan. 2004.



How to Cite

Bhargava, S., Kumar , M. R., Mehta, P., Mathews, J., Kumar, S., & Babu, C. S. (2021). A Novel Example-Dependent Cost-Sensitive Stacking Classifier to Identify Tax Return Defaulters. Business Information Systems, 1, 343–353. https://doi.org/10.52825/bis.v1i.61

Conference Proceedings Volume