PROBLEM STATEMENT
Problem Statement
The general problem to be addressed is the complexity and sophistication of fraudulent
activities resulting in challenges for organizations in detecting, preventing, and deterring fraud.
ACFE (2020) determined that the estimated costs of complex and sophisticated fraudulent
activities such as pharming costs organizations 5% of revenues each year, projecting nearly $4.5
trillion in fraud loses globally. This scale of fraud can lead to significant global financial crises
and bankruptcy of companies if governments and business communities does not deploy a sense
of urgency to address the complexity and sophistication of fraudulent activities which continue
to evade most of the traditional methods used in fraud detection, prevention and detection. In a
recent study, Roszkowska (2021) found that artificial intelligence algorithms were vital to the
analysis of large data sets and the identification of patterns of fraudulent activities. Akinbowale
et. al (2022) supported these claims by demonstrating that the multi-objectives integer
programming model outperforms traditional methods of forensic accounting.
Lokanan and Vuong (2019) supported these claims by explaining that detection,
prevention, and deterrence of financial anomalies in the financial service industry were achieved
more accurately by machine learning algorithms rather than traditional methods. Bhattacharya
et. al (2022) found that applications of artificial intelligence in the financial services industry
serves a dual purpose of enhancing customer experience and improves the algorithms needed to
boost decision making in the detection, prevention and deterrence of fraudulent financial
transactions and schemes. The specific problem to be addressed is the complexity and
sophistication of fraudulent activities within the financial industry resulting in challenges for
PROBLEM STATEMENT
References
Association of Certified Fraud Examiners (ACFE). (2020). Report to the nations: 2020
global on study on occupational fraud and abuse. https://acfepublic.s3-us-west-
2.amazonaws.com/2020-Report-to-the-Nations.pdf
Akinbowale, Klingelhöfer, H. E., & Zerihun, M. F. (2022). Development of a multi-objectives
integer programming model for allocation of anti-fraud capacities during cyberfraud
mitigation. Journal of Financial Crime., ahead-of-print(ahead-of-print).
https://doi.org/10.1108/JFC-10-2022-0245
Lokanan, Tran, V., & Vuong, N. H. (2019). Detecting anomalies in financial statements using
machine learning algorithm. AJAR (Asian Journal of Accounting Research), 4(2), 181–
201. https://doi.org/10.1108/AJAR-09-2018-0032
Roszkowska, P. (2021). Fintech in financial reporting and audit for fraud prevention and
safeguarding equity investments. Journal of Accounting & Organizational Change,
17(2), 164-196. https://doi.org/10.1108/JAOC-09-2019-0098
Powered by TCPDF (www.tcpdf.org)
