Shell Companies: Using a hybrid technique to detect illicit activities

Allbwn ymchwil: Cyfraniad at gynhadleddPapur

StandardStandard

Shell Companies: Using a hybrid technique to detect illicit activities. / Tiwari, Milind; Gepp, Adrian; Kumar, Kuldeep.
2021.

Allbwn ymchwil: Cyfraniad at gynhadleddPapur

HarvardHarvard

APA

CBE

MLA

VancouverVancouver

Author

RIS

TY - CONF

T1 - Shell Companies: Using a hybrid technique to detect illicit activities

AU - Tiwari, Milind

AU - Gepp, Adrian

AU - Kumar, Kuldeep

N1 - 2021 Accounting and Finance Association of Australia and New Zealand (AFAANZ) Virtual Conference, AFAANZ ; Conference date: 05-07-2021 Through 07-07-2021

PY - 2021/7/6

Y1 - 2021/7/6

N2 - 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.

AB - 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.

M3 - Paper

ER -