The Self-Organizing Map in Selecting Companies for Tax Audit

  • Minna Kallio
  • Barbro Back


Today, Tax Authorities receive the tax reports from companies to a large extent in digital form from the companies in Finland. Most of the tax reports are processed routinely i.e., a computer program checks that the taxes paid in advance are the correct ones and if not, the company either receives a tax return or is asked to pay the difference and there is no need for a tax audit. However, there is a small percentage of companies that need it. Most of these companies – for some reason – have not reported all their income items or have reported cost items that do not belong to their report. This could be unintended or it could be fraud. The problem is to find this percentage from the mass of tax reports. So far, the tax auditors or tax inspectors have used their past experience and posed queries to the data base, where the reports are stored, to find the ones that need a tax audit. This is not necessarily the most effective way of finding the tax reports that need a tax audit. Different data mining tools might aid in this process and make the selections of companies that need tax audit more effective. The aim of this paper is to investigate how well an unsupervised neural network method – the self-organizing map (SOM) – can perform in the task of finding the companies that need to be tax audited. SOM is a data driven approach without a need to have predefined rules or sets of values. A real data set is used and the results are compared to the results that the tax inspectors have received with their methods.


Feature Plane Inspection Result Taxation Data Input Data Vector Income Item 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bakin, S., Hegland, M., Williams, G. (1999) Mining Taxation Data with Parallel BMARSin http://zSzzSzresearch.cmis.csiro.SzgjwzSzpaperszSzatobmars.pdf/bakin99mining.pdf, 06.06.2006.
  2. 2.
    DeBarr, D., and Euler-Walker Z., (2006) Closing the gap: Automated screening tax returns to identify egregious tax shelters. SIGKDD Explorations, 8(1), 11-16.CrossRefGoogle Scholar
  3. 3.
    Bonchi, F., Giannotti, F., Mainetto, G.,and Pedreschi, D., (1999) Using data mining techniques in fiscal fraud detection, in Mukesh Mohania and A Min Tjoa eds., DaWaK’99, LNCS 1676, 369-376,Heidelberg, 11.09.2006.
  4. 4.
    Bonner, S. E., Palmrose, Z-V., and Young S. M., (1998) Fraud type and auditor litigation: An analysis of accounting and auditing enforcement releases. The Accounting Review, 73(4), October, 503-532.Google Scholar
  5. 5.
    Denny, Williams. G. J.,and Christen P., (2008) Exploratory hot spot profile analysis using interactive visual drill-down self-organizing maps. Advances in Knowledge Discoveryand Data Mining:12th Pasific-Asia Conference, PAKDD 2008, Osaka, Japan, May 2008.Google Scholar
  6. 6.
    Danziger, J. N., Andersen K., (2002), The impacts of information technology on public administration: an analysis of empirical research from the “golden age” of transformation. International Journal of Public Administration, 25(5), 591-627.CrossRefGoogle Scholar
  7. 7.
    Eilifsen, A., Knivsflå, K. H., and Sættem F., (1999) Earnings manipulation: cost of capital versus tax. European Accounting Review, 8(3), 481-491.CrossRefGoogle Scholar
  8. 8.
    Eklund, T., (2004) The Self-organizing Map in Financial Benchmarking. TUCS Dissertations No 56.9. Fisher, R., (1997) Determination of residence status for taxation law: Development of a rule-based expert system, Melbourne, Australia. ACM Press, 161-169.Google Scholar
  9. 9.
    Kohonen, T., (2001) Self-Organizing Maps, 3rd ed.Springer Verlag, Berlin.Google Scholar
  10. 10.
    Koskivaara, E., (2004) Artificial Neural Networks for Analytical Review in Auditing . Turku School of Economics and Business Administration. Series A-7:2004.Google Scholar
  11. 11.
    Kotsiantis, S., Koumanakos, E., Tzelepis, D., and Tampakas, V., (2006) Forecasting fraudulent financial statements using data mining. International Journal of Computational Intelligence, 3(2), 104-110.Google Scholar
  12. 12.
    Lange, G. A., (2001) Fraudulent financial reporting in Encyclopaedia of business and finance ed. by Kaliski Burton S., USA.Google Scholar
  13. 13.
    Pyle, D., (1999) Data preparation for data mining, USA.Google Scholar
  14. 14.
    Smith, K., (2002) Neural Networks in Business: Techniques and Applications, USAGoogle Scholar
  15. 15.
    Spathis, C. T., (2002) Detecting false financial statements using published data: some evidence from Greece., Managerial Auditing Journal, 17(4), 179-191.Google Scholar
  16. 16.
    Spathis, Ch., Dumps’, M., and Zopoudinis, C., (2002) Detecting falsified financial statements: a comparative study using multicriteria analysis and multivariate statistical techniques. The European Accounting Review, 11(3), 509-535.CrossRefGoogle Scholar
  17. 17.
    Tan, R. P. G. H., van der Berg, J., and van der Berg, M., (2002) Credit Rating Classification Using Self Organizing Maps, in Neural Networks in Business: Techniques and Applications Smith Kate, ed., USA, 2002, 140-153.Google Scholar
  18. 18.
    Vesanto, J., (1999) SOM-based data visualization methods. Intelligent Data Analysis, 3Google Scholar
  19. 19.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Minna Kallio
    • 1
  • Barbro Back
    • 1
  1. 1.Department of Information TechnologiesÅbo Akademi UniversityTurkuFinland

Personalised recommendations