Detecting value-added tax evasion by business entities of Kazakhstan

Zhenisbek Assylbekov, Igor Melnykov, Rustam Bekishev, Assel Baltabayeva, Dariya Bissengaliyeva, Eldar Mamlin

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    13 Citations (Scopus)

    Abstract

    This paper presents a statistics-based method for detecting value-added tax evasion by Kazakhstani legal entities. Starting from features selection we perform an initial exploratory data analysis using Kohonen self-organizing maps; this allows us to make basic assumptions on the nature of tax compliant companies. Then we select a statistical model and propose an algorithm to estimate its parameters in unsupervisedmanner. Statistical approach appears to benefit the task of detecting tax evasion: our model outperforms the scoring model used by the State Revenue Committee of the Republic of Kazakhstan demonstrating significantly closer association between scores and audit results.

    Original languageEnglish
    Title of host publicationIntelligent Decision Technologies 2016 - Proceedings of the 8th KES International Conference on Intelligent Decision Technologies, KES-IDT 2016
    PublisherSpringer Science and Business Media Deutschland GmbH
    Pages37-49
    Number of pages13
    Volume56
    ISBN (Print)9783319396293
    DOIs
    Publication statusPublished - 2016
    Event8th KES International Conference on Intelligent Decision Technologies, KES-IDT 2016 - Puerto de la Cruz, Tenerife, Spain
    Duration: Jun 15 2016Jun 17 2016

    Publication series

    NameSmart Innovation, Systems and Technologies
    Volume56
    ISSN (Print)21903018
    ISSN (Electronic)21903026

    Other

    Other8th KES International Conference on Intelligent Decision Technologies, KES-IDT 2016
    CountrySpain
    CityPuerto de la Cruz, Tenerife
    Period6/15/166/17/16

    Keywords

    • Anomaly detection
    • Cluster analysis
    • Self-organizing maps
    • Tax evasion detection

    ASJC Scopus subject areas

    • Computer Science(all)
    • Decision Sciences(all)

    Fingerprint Dive into the research topics of 'Detecting value-added tax evasion by business entities of Kazakhstan'. Together they form a unique fingerprint.

    Cite this