• TUCS Publication Series
• How to Publish in TUCS Series
• Publication Search
• Publication Graph
• Publication Input
• Publication Input Guide
• JuFo Browser

The Self-Organizing Map in Selecting Companies for Tax Auditing

Barbro Back, Minna Kallio, The Self-Organizing Map in Selecting Companies for Tax Auditing. In: The 32nd Annual Congress of the European Accounting Association, Tampere, Finland,2009, 2009.

Abstract:

Today, tax authorities receive the tax reports from companies to a large extent in digital form from the companies in our country. 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 to a deeper inspection of them. However, there is a small percentage of companies that need a deeper inspection of their tax reports, mostly companies that for some reason have not reported all their income items or have reported cost items that do not belong to their report - it 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 inspection. This is not necessarily, the most effective way of finding the tax reports that need inspection. Different data mining tools might aid in this process and make the selections of companies that need inspection more effective. Neural networks belong to the family of data mining tools that are used for similar kinds of tasks. There are two main types of neural networks - supervised and unsupervised methods. Our aim is to investigate how well an unsupervised method - the self-organizing map (SOM) - can perform in the task of finding the companies that need inspection. SOM is a data driven approach without a need to have predefined rules or sets of values. We use a real data set and we compare our results to the results that the tax inspectors have received with their methods.

BibTeX entry:

@INPROCEEDINGS{inpBaKa09a,
  title = {The Self-Organizing Map in Selecting Companies for Tax Auditing},
  booktitle = {The 32nd Annual Congress of the European Accounting Association, Tampere, Finland,2009},
  author = {Back, Barbro and Kallio, Minna},
  year = {2009},
  keywords = {Self-Organizing Map, tax auditing, fraud},
}

Belongs to TUCS Research Unit(s): Data Mining and Knowledge Management Laboratory

Edit publication