Skip to main navigation Skip to search Skip to main content

Shell Companies: Using a hybrid technique to detect illicit activities

Research output: Contribution to conference › Poster › Research › peer-review

737 Downloads (Pure)

Abstract

Shell companies can be used to launder dirty money to make it appear legitimate and hide information about the actual beneficial owners. Illegal arms dealers, drug cartels, corrupt politicians, terrorists and cyber-criminals have become some of the frequent users of shell companies. This study aims to develop a model for detecting shell companies being used to launder illicit proceeds of crime using a new hybrid statistical approach. Using a combination of graph algorithms and supervised learning, detection models with classification accuracy ranging between 88.17% and 97.85%, were developed to detect illicit entities. To the best of our knowledge, no prior study exists on developing quantitative models to detect illicit shell companies using publicly available information. The key stakeholders to benefit from such models would be legal and compliant professionals and government officials, especially accountants, tax officials and anti-corruption NGOs.
Original languageEnglish
Publication statusUnpublished - 6 Jul 2021
Event2021 Accounting and Finance Association of Australia and New Zealand (AFAANZ) Virtual Conference - Virtual
Duration: 5 Jul 2021 → 7 Jul 2021
Conference number: 2021
https://www.afaanz.org/2021-afaanz-virtual-conference

Conference

Conference2021 Accounting and Finance Association of Australia and New Zealand (AFAANZ) Virtual Conference
Abbreviated titleAFAANZ
Period5/07/21 → 7/07/21
Internet address

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 16 - Peace, Justice and Strong Institutions
    SDG 16 Peace, Justice and Strong Institutions

Fingerprint

Dive into the research topics of 'Shell Companies: Using a hybrid technique to detect illicit activities'. Together they form a unique fingerprint.

Cite this