The use of business intelligence and predictive analytics in detecting and managing occupational fraud in Nigerian banks

Chioma N. Nwafor*, Obumneme Z. Nwafor, Chris Onalo

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

The problem of occupational fraud is one of the most wide-reaching operational risk event types in the Nigerian banking system. This event type spans many departments, roles, processes and systems and causes significant financial and reputational damage to banks. As a result, fraud presents banks with a real challenge in terms of knowing where to start. One of the main aims of this paper is to use stochastic probability models to predict aggregate fraud severity and fraud frequency within the Nigerian banking sector using historical data. Another objective is to describe how banks can develop and deploy business intelligence (BI) outlier-based detection models to recognize internal fraudulent activities. As the volume of transaction data grows and the industry focuses more closely on fraud detection, BI has evolved to provide proactive, real-time insights into fraudulent behaviors and activities. We discuss the fraud analytic development process, since it is a central issue in real application domains.
Original languageEnglish
Pages (from-to)95-120
Number of pages26
JournalJournal of Operational Risk
Volume14
Issue number3
Early online date4 Sep 2019
DOIs
Publication statusPublished - Sep 2019

Fingerprint

Fraud
Business intelligence
Outliers
Banking sector
Operational risk
Severity
Banking system
Probability model
Fraud detection
Development process
Industry
Transaction data
Damage

Keywords

  • business intelligence
  • predictive analytics
  • operational risk
  • fraud
  • outlier detection

Cite this

@article{d629fbc0adb14a80aede04e4205eb039,
title = "The use of business intelligence and predictive analytics in detecting and managing occupational fraud in Nigerian banks",
abstract = "The problem of occupational fraud is one of the most wide-reaching operational risk event types in the Nigerian banking system. This event type spans many departments, roles, processes and systems and causes significant financial and reputational damage to banks. As a result, fraud presents banks with a real challenge in terms of knowing where to start. One of the main aims of this paper is to use stochastic probability models to predict aggregate fraud severity and fraud frequency within the Nigerian banking sector using historical data. Another objective is to describe how banks can develop and deploy business intelligence (BI) outlier-based detection models to recognize internal fraudulent activities. As the volume of transaction data grows and the industry focuses more closely on fraud detection, BI has evolved to provide proactive, real-time insights into fraudulent behaviors and activities. We discuss the fraud analytic development process, since it is a central issue in real application domains.",
keywords = "business intelligence, predictive analytics, operational risk, fraud, outlier detection",
author = "Nwafor, {Chioma N.} and Nwafor, {Obumneme Z.} and Chris Onalo",
note = "Acceptance in SAN AAM: not permitted by publisher (https://www.risk.net/static/copyright-and-permissions); only VoR permitted; VoR unavailable as outwith GCU subscription to journal. Have asked author to provide VoR, if possible. 8/11/19 DC",
year = "2019",
month = "9",
doi = "10.21314/JOP.2019.227",
language = "English",
volume = "14",
pages = "95--120",
journal = "Journal of Operational Risk",
issn = "1744-6740",
publisher = "Incisive Media",
number = "3",

}

The use of business intelligence and predictive analytics in detecting and managing occupational fraud in Nigerian banks. / Nwafor, Chioma N.; Nwafor, Obumneme Z.; Onalo, Chris.

In: Journal of Operational Risk, Vol. 14, No. 3, 09.2019, p. 95-120.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The use of business intelligence and predictive analytics in detecting and managing occupational fraud in Nigerian banks

AU - Nwafor, Chioma N.

AU - Nwafor, Obumneme Z.

AU - Onalo, Chris

N1 - Acceptance in SAN AAM: not permitted by publisher (https://www.risk.net/static/copyright-and-permissions); only VoR permitted; VoR unavailable as outwith GCU subscription to journal. Have asked author to provide VoR, if possible. 8/11/19 DC

PY - 2019/9

Y1 - 2019/9

N2 - The problem of occupational fraud is one of the most wide-reaching operational risk event types in the Nigerian banking system. This event type spans many departments, roles, processes and systems and causes significant financial and reputational damage to banks. As a result, fraud presents banks with a real challenge in terms of knowing where to start. One of the main aims of this paper is to use stochastic probability models to predict aggregate fraud severity and fraud frequency within the Nigerian banking sector using historical data. Another objective is to describe how banks can develop and deploy business intelligence (BI) outlier-based detection models to recognize internal fraudulent activities. As the volume of transaction data grows and the industry focuses more closely on fraud detection, BI has evolved to provide proactive, real-time insights into fraudulent behaviors and activities. We discuss the fraud analytic development process, since it is a central issue in real application domains.

AB - The problem of occupational fraud is one of the most wide-reaching operational risk event types in the Nigerian banking system. This event type spans many departments, roles, processes and systems and causes significant financial and reputational damage to banks. As a result, fraud presents banks with a real challenge in terms of knowing where to start. One of the main aims of this paper is to use stochastic probability models to predict aggregate fraud severity and fraud frequency within the Nigerian banking sector using historical data. Another objective is to describe how banks can develop and deploy business intelligence (BI) outlier-based detection models to recognize internal fraudulent activities. As the volume of transaction data grows and the industry focuses more closely on fraud detection, BI has evolved to provide proactive, real-time insights into fraudulent behaviors and activities. We discuss the fraud analytic development process, since it is a central issue in real application domains.

KW - business intelligence

KW - predictive analytics

KW - operational risk

KW - fraud

KW - outlier detection

U2 - 10.21314/JOP.2019.227

DO - 10.21314/JOP.2019.227

M3 - Article

VL - 14

SP - 95

EP - 120

JO - Journal of Operational Risk

JF - Journal of Operational Risk

SN - 1744-6740

IS - 3

ER -