Application of Kohonen Maps in Predicting and Characterizing VAT Fraud in a Sub-Saharan African Country

Ricardo Santos, Ricardo Moura, Victor Lobo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.
Original languageEnglish
Title of host publicationAdvances in Self-Organizing Maps, Learning Vector Quantization, Clustering and Data Visualization
Subtitle of host publicationDedicated to the Memory of Teuvo Kohonen / Proceedings of the 14th International Workshop, WSOM+ 2022, Prague, Czechia, July 6-7, 2022
EditorsJan Faigl, Madalina Olteanu, Jan Drchal
PublisherSpringer, Cham
Chapter8
Pages74-86
ISBN (Electronic)978-3-031-15444-7
ISBN (Print)978-3-031-15443-0
DOIs
Publication statusPublished - 27 Aug 2022
Event14th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM+ 2022) - Prague, Czech Republic
Duration: 6 Jul 20228 Jul 2022
Conference number: 14

Publication series

NameLecture Notes in Networks and Systems
Volume533
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference14th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM+ 2022)
Abbreviated titleWSOM 2022
Country/TerritoryCzech Republic
CityPrague
Period6/07/228/07/22

Keywords

  • VAT
  • Fraud
  • Self-organizing maps
  • Audit
  • data mining

Fingerprint

Dive into the research topics of 'Application of Kohonen Maps in Predicting and Characterizing VAT Fraud in a Sub-Saharan African Country'. Together they form a unique fingerprint.

Cite this