Artificial neural network methodology in financial statements fraud: An empirical study in the property and real estate sector

Download This Article

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Financial statements are crucial reports for stakeholders to assess a company’s financial condition. However, they are susceptible to fraud, with financial statement fraud representing the type with the largest losses in 2024, amounting to $766,000 (Association of Certified Fraud Examiners [ACFE], 2024). In response to this significant issue, the International Federation of Accountants (IFAC, 2009) issued the International Standard on Auditing (ISA) 240, which highlights three factors contributing to fraud: 1) pressure, 2) opportunity, and 3) rationalization, known as the fraud triangle. This study aims to analyze the impact of these fraud triangle factors on financial statement fraud in property and real estate sector companies listed on the stock exchanges of the Association of Southeast Asian Nations (ASEAN) countries during the 2021–2022 period. The study population comprises property and real estate companies in ASEAN, with a sample size of 170 companies, totaling 340 observations over a two-year period. Secondary data were collected from the OSIRIS database, and a purposive sampling technique was used. The data analysis method involved an artificial neural network (ANN) analysis with IBM SPSS 25 software. The prediction results showed an accuracy level of 81.3 percent. This study provides empirical evidence that pressure, opportunity, and rationalization significantly influence financial statement fraud, supporting the fraud triangle theory in explaining this phenomenon.

Keywords: Association of Southeast Asian Nations, Artificial Neural Network, Fraud Triangle, Financial Statement Fraud, Property and Real Estate

Authors’ individual contribution: Conceptualization — D.V.R.W.R. and R.W.; Methodology — D.V.R.W.R. and R.W.; Formal Analysis — D.V.R.W.R. and R.W.; Investigation — D.V.R.W.R. and R.W.; Data Curation — D.V.R.W.R. and R.W.; Writing — Original Draft — D.V.R.W.R. and R.W.; Writing — Review & Editing — D.V.R.W.R. and R.W.; Visualization — D.V.R.W.R. and R.W.

Declaration of conflicting interests: The Authors declare that there is no conflict of interest.

JEL Classification: C45, L85, M42

Received: 06.08.2024
Revised: 13.11.2024; 17.12.2024; 05.03.2025
Accepted: 17.03.2025
Published online: 20.03.2025

How to cite this paper: Rahayu, D. V. R. W., & Widuri, R. (2025). Artificial neural network methodology in financial statements fraud: An empirical study in the property and real estate sector [Special issue]. Risk Governance & Control: Financial Markets & Institutions, 15(1), 237–248. https://doi.org/10.22495/rgcv15i1sip9