Abstract
This paper describes the use Self-Organizing Maps (or Kohonen Networks) in helping to detect Value Added Tax (VAT) fraud. The sub-Saharan African Country presented as a case study has had its largest share in tax revenues since the introduction of VAT, nearly two decades ago, but still has a relatively modest tax efficiency when compared to European or worldwide standards. This trend can be reversed by strengthening the audit and inspection processes of its Revenue Authority (RA) with Data Mining, taking advantage of historical data stored by different information systems. A Case Study in the southern region of this country is presented, where historical data available from tax audits are compared with the VAT returns using Kohonen Maps. Comparing the experimental results with other anomaly detection algorithms, Kohonen maps prove to be of great value in predicting and characterizing VAT fraud in this case study.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Approximately 0.44% of the taxpayers, among which 91.6% are positive cases of fraud, typically unbalanced and biased dataset [29].
- 2.
Samples from other VAT regimes or with invalid/non-existent TIN are excluded.
- 3.
States that once registered as a positive case of fraud, the Taxpayer tends to relapse into fraudulent practices in future fiscal years.
- 4.
References
Hajdúchová, I., sedltačiková, M., Viszlat, I.: Value-added tax impact on the state budget expenditures and incomes. Procedia Econ. Finance, 34, 676–681 (2015)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn., pp. 1–19. Wiley, Hoboken (2000)
Krever, R.: VAT in Africa, pp. 71–80. Pretoria University Law Press, Pretoria (2008)
La Feria, R., Schoeman, A.: Addressing VAT fraud in developing countries: the tax policy-administration symbiosis. Intertax 47(11), 950–967 (2019)
IMF: Digital Revolutions in Public Finance (2017). https://doi.org/10.5089/9781484315224.071. Accessed 25 May 2021
Mwanza, M., Phiri, J.: Fraud detection on bulk tax data using business intelligence data mining tool: a case of Zambia revenue authority. Int. J. Adv. Res. Comput. Commun. Eng. 5(3), 793–798 (2016)
De Roux, D., Pérez, B., Moreno, A., Villamtl, M.D.P., Figueroa, C.: Tax fraud detection for under-reporting declarations using an unsupervised machine learning approach. In: KDD, 19–23 August 2018, London, UK, pp. 215–222 (2018)
Jihal, H., Talhaou, M.A., Daif, A., Azzouazi, M.: Predictive analytics as a service on moroccan tax evasion. Int. J. Eng. Technol. 7(432), 90–92 (2018)
Jupri, M., Sarno, R.: Data mining, fuzzy AHP and TOPSIS for optimizing taxpayer supervision. Indonesian J. Electr. Eng. Comput. Sci. 18(1), 75–87 (2020)
Kohonen, T.: Self-organized formation of topologically correct feature maps. Biol. Cybern. 43(1), 59–69 (1982). https://doi.org/10.1007/BF00337288
Wendel, J., Buttenfield, B.: Formalizing guidelines for building meaningful self-organizing maps. In: GIScience 2010: Sixth international conference on Geographic Information Science. Zurich, 14-17th September (2010)
Tu, L.A., Thai, V.D., Hoan, N.Q.: Improving feature map quality of SOM based on adjusting the neighborhood function. Int. J. Comput. Sci. Inf. Secur. (IJCSIS) 14(9), 1–6 (2016)
Kohonen, T., Schroeder, M.R., Huang, T.S.: Self-Organizing Maps, 3rd edn. Springer-Verlag, Berlin, Heidelberg (2001). https://doi.org/10.1007/978-3-642-56927-2
Ultsch, A: U*-Matrix: a Tool to visualize Clusters in high dimensional Data. DataBionics Research Lab, Department of Computer Science University of Marburg, Technical report no. 36 (2003)
Serrano-Cinca C.: Let Financial Data Speak for Themselves. In: Deboeck, G., Kohonen, T. (eds.) Visual Explorations in Finance with Self-Organizing Maps. Springer Finance. Springer, London. pp. 3–18 (1998). https://doi.org/10.1007/978-1-4471-3913-3_1
Kiviluoto, K., Bergius, P.: Maps for analyzing failures of small and medium-sized enterprises. In: Deboeck, G., Kohonen, T. (eds.) Visual Explorations in Finance with Self-Organizing Maps. Springer Finance. Springer, London. pp. 59-71 (1998). https://doi.org/10.1007/978-1-4471-3913-3_4
Tian, J., Azarian, M.H., Pecht, M.: Anomaly detection using self-organizing maps-based k-nearest neighbor algorithm. In: PHM Society European Conference, vol. 2, no. 1, pp. 3–4 (2014)
Steinhaus, H.: Sur la division des corps matériels en parties. Bull. Acad. Polon. Sci. 4(12), 801–804 (1957)
Fix, E., Hodges, J.L.: Discriminatory Analysis. Consistency Properties. USAF School of Aviation Medicine, Randolph Field, Texas, Nonparametric Discrimination (1951)
Breunig, M.M., Kriegel, H., NG, R.T., Sander, J. : LOF: identifying density-based local outliers. In: SIGMOD Rec, vol. 29, 2 June, pp. 93-104 (2000)
Schölkopf, B., Williamson, R.C., Smola, A.J., Shawe-Tay, J., PLATT, J.C.: Support vector method for novelty detection. In: NIPS 1999 Proceedings of the 12th International Conference on Neural Information Processing Systems, November, pp. 582–588 (1999)
Cnossen, S.: Mobilizing VAT revenues in African countries. Int. Tax Public Fin. 22(6), 1077–1108 (2015). https://doi.org/10.1007/s10797-015-9348-1
Wu, R., Ou, C.S., Lin, H., Chang, S., Yen, D.C.: Using data mining technique to enhance tax evasion detection performance. Expert Syst. Appl. 39, 8769–8777 (2012)
Basta, S., et al.: High quality true-positive prediction for fiscal fraud detection. In: 2009 IEEE International Conference on Data Mining Workshops (2009)
Vanhoeyveld, J., Martens, D., Peeters, B.: Value-added tax fraud detection with scalable anomaly detection techniques. Appl. Soft Comput. J. 8640, 1–20 (2019)
Mittal, S., Reich, O., Mahajan, A.: Who is bogus? using one-sided labels to identify fraudulent firms from tax returns. In: Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies, in COMPASS 2018. ACM, New York, NY, USA, pp. 24:1–24:11 (2018)
Matos, T., Macedo, J.A.F., Monteiro, J.M.: An empirical method for discovering tax fraudsters: a real case study of Brazilian fiscal evasion. In: Proceedings of the 19th International Database Engineering No. 38, Applications Symposium, in IDEAS 2015. ACM, New York, NY, USA, pp. 41-48 (2015)
Pironet, M.: Classification for Fraud Detection with Social Network Analysis. Master’s Thesis, Instituto Superior Técnico. Department of Computer Engineering. Master in Informatics and Computer Engineering (2009)
Guarascio, M.: Data Mining Techniques for Fraud Detection. Ph. D thesis, Universitádella Calabria. Dipartimento di Elletronica, Informatica e Sistemistica. Dottorato di Ricerca in Ingegneria dei Sistemi e Informatica. Ciclo XXII (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix A - Component Maps
Appendix A - Component Maps
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Santos, R., Moura, R., Lobo, V. (2022). Application of Kohonen Maps in Predicting and Characterizing VAT Fraud in a Sub-Saharan African Country. In: Faigl, J., Olteanu, M., Drchal, J. (eds) Advances in Self-Organizing Maps, Learning Vector Quantization, Clustering and Data Visualization. WSOM+ 2022. Lecture Notes in Networks and Systems, vol 533. Springer, Cham. https://doi.org/10.1007/978-3-031-15444-7_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-15444-7_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15443-0
Online ISBN: 978-3-031-15444-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)