Improving models that detect financial statement fraud: A new framework to guide variable selection

Adrian Gepp, Kuldeep Kumar, Sukanto Bhattacharya

Research output: Contribution to conferenceAbstractResearchpeer-review

Abstract

Financial statement fraud is a costly problem for society and so better aids, such as detection models, are needed to make detection faster and more effective. The choice of which independent variables to use in such models is crucial, but surprisingly the selection process in prior research is not standardised. Consequently, a new framework is proposed for this, the Fraud Detection Triangle (FDT). The FDT adapts the well-known Fraud Triangle, which was originally designed to explain the drivers of fraudulent behaviour rather than its detection. Each original factor is extended, and a new one, Suspicious Information, is included.
Original languageEnglish
Publication statusPublished - 2016
EventAccounting and Finance Association of Australia and New Zealand (AFAANZ) 2016 - Jupiters Hotel, Gold Coast, Australia
Duration: 3 Jul 20165 Jul 2016
http://www.afaanz.org/conferences

Conference

ConferenceAccounting and Finance Association of Australia and New Zealand (AFAANZ) 2016
Abbreviated titleAFAANZ
CountryAustralia
CityGold Coast
Period3/07/165/07/16
Internet address

Fingerprint

Financial statement fraud
Variable selection
Fraud detection
Factors
Fraud
Selection process

Cite this

Gepp, A., Kumar, K., & Bhattacharya, S. (2016). Improving models that detect financial statement fraud: A new framework to guide variable selection. Abstract from Accounting and Finance Association of Australia and New Zealand (AFAANZ) 2016, Gold Coast, Australia.
Gepp, Adrian ; Kumar, Kuldeep ; Bhattacharya, Sukanto. / Improving models that detect financial statement fraud : A new framework to guide variable selection. Abstract from Accounting and Finance Association of Australia and New Zealand (AFAANZ) 2016, Gold Coast, Australia.
@conference{e2fac6b5c1104dba946386be73b43850,
title = "Improving models that detect financial statement fraud: A new framework to guide variable selection",
abstract = "Financial statement fraud is a costly problem for society and so better aids, such as detection models, are needed to make detection faster and more effective. The choice of which independent variables to use in such models is crucial, but surprisingly the selection process in prior research is not standardised. Consequently, a new framework is proposed for this, the Fraud Detection Triangle (FDT). The FDT adapts the well-known Fraud Triangle, which was originally designed to explain the drivers of fraudulent behaviour rather than its detection. Each original factor is extended, and a new one, Suspicious Information, is included.",
author = "Adrian Gepp and Kuldeep Kumar and Sukanto Bhattacharya",
year = "2016",
language = "English",
note = "Accounting and Finance Association of Australia and New Zealand (AFAANZ) 2016, AFAANZ ; Conference date: 03-07-2016 Through 05-07-2016",
url = "http://www.afaanz.org/conferences",

}

Gepp, A, Kumar, K & Bhattacharya, S 2016, 'Improving models that detect financial statement fraud: A new framework to guide variable selection' Accounting and Finance Association of Australia and New Zealand (AFAANZ) 2016, Gold Coast, Australia, 3/07/16 - 5/07/16, .

Improving models that detect financial statement fraud : A new framework to guide variable selection. / Gepp, Adrian; Kumar, Kuldeep; Bhattacharya, Sukanto.

2016. Abstract from Accounting and Finance Association of Australia and New Zealand (AFAANZ) 2016, Gold Coast, Australia.

Research output: Contribution to conferenceAbstractResearchpeer-review

TY - CONF

T1 - Improving models that detect financial statement fraud

T2 - A new framework to guide variable selection

AU - Gepp, Adrian

AU - Kumar, Kuldeep

AU - Bhattacharya, Sukanto

PY - 2016

Y1 - 2016

N2 - Financial statement fraud is a costly problem for society and so better aids, such as detection models, are needed to make detection faster and more effective. The choice of which independent variables to use in such models is crucial, but surprisingly the selection process in prior research is not standardised. Consequently, a new framework is proposed for this, the Fraud Detection Triangle (FDT). The FDT adapts the well-known Fraud Triangle, which was originally designed to explain the drivers of fraudulent behaviour rather than its detection. Each original factor is extended, and a new one, Suspicious Information, is included.

AB - Financial statement fraud is a costly problem for society and so better aids, such as detection models, are needed to make detection faster and more effective. The choice of which independent variables to use in such models is crucial, but surprisingly the selection process in prior research is not standardised. Consequently, a new framework is proposed for this, the Fraud Detection Triangle (FDT). The FDT adapts the well-known Fraud Triangle, which was originally designed to explain the drivers of fraudulent behaviour rather than its detection. Each original factor is extended, and a new one, Suspicious Information, is included.

M3 - Abstract

ER -

Gepp A, Kumar K, Bhattacharya S. Improving models that detect financial statement fraud: A new framework to guide variable selection. 2016. Abstract from Accounting and Finance Association of Australia and New Zealand (AFAANZ) 2016, Gold Coast, Australia.