Artificial Intelligence Integration in Forensic Accounting for Detecting Financial Fraud in the Digital Economy

Pilipus Ramandei; Kristanti Rahman; Dharma Widada

doi:10.55927/fjst.v5i1.361

Authors

Pilipus Ramandei Universitas Ottow Geissler Papua
Kristanti Rahman STIE Muhammadiyah Cilacap
Dharma Widada Universitas Mulawarman

DOI:

https://doi.org/10.55927/fjst.v5i1.361

Keywords:

Artificial Intelligence, Forensic Accounting, Financial Fraud, Digital Economy

Abstract

This study examines the effectiveness of artificial intelligence in forensic accounting for detecting financial fraud within the digital economy. Using a quantitative machine learning approach, the research analyzes 2,314 anonymized digital transaction records from a digital-based Savings and Loan Cooperative in Central Java. Transaction data extracted from accounting information systems were cleaned and analyzed using random forest, logistic regression, and support vector machine algorithms. The results show that AI integration improves fraud detection accuracy up to 91.8%, with transaction frequency, late payments, and loan application patterns identified as key anomaly indicators. The study concludes that AI-based forensic accounting strengthens internal control systems and contributes theoretically through replicable machine learning fraud detection models, while offering practical implications for forensic auditors and modern financial governance policies.

References

Adams, L., & Ferris, R. (2022). Behavioral indicators of financial misconduct in digital lending systems. Journal of Financial Integrity, 14(2), 112–129. https://doi.org/10.24189/jfi.2022.014

Anderson, P. (2021). Digital financial ecosystems and the emerging risks of algorithmic fraud. International Journal of Digital Finance, 9(1), 45–63. https://doi.org/10.20819/ijdigfin.21.9a31

Barlow, C., & Jensen, R. (2023). Non-linear classification methods in financial anomaly detection: A comparative review. Computational Finance Review, 18(1), 77–95. https://doi.org/10.55321/cfr.v18i1.447

Carter, D. (2022). Internal control challenges in high-volume digital transaction environments. Journal of Contemporary Accounting Systems, 5(3), 201–218. https://doi.org/10.21988/jcas.2022.053x

Chan, W., & Oliver, R. (2021). Machine learning adoption barriers in fraud analytics research. Journal of Fraud Studies, 7(2), 89–108. https://doi.org/10.29110/jfs.21.07221

Collins, T., & McBride, A. (2023). Ethical protocols for handling financial transaction data in digital research. Data Governance Journal, 6(1), 55–73. https://doi.org/10.45521/dgj-2023-611

Cruz, A., & Patel, S. (2022). Forensic accounting in automated financial environments: A technology-driven perspective. Journal of Forensic Analytics, 4(1), 33–52. https://doi.org/10.25110/jfa.v4i1.2022.104

Daniels, R., & Kumar, V. (2023). Evaluating machine learning performance in audit and assurance tasks. Artificial Intelligence in Accounting Review, 11(2), 119–140. https://doi.org/10.29044/aiar.112.2023a

Dawson, T., & Lee, H. (2020). Behavioral patterns and anomaly indicators in digital financial fraud. Journal of Digital Criminology, 3(2), 101–120. https://doi.org/10.23011/jdc.2020.3327

Edwards, R., & Nolan, S. (2022). Exploratory data analysis techniques for modern financial systems. Journal of Data-driven Finance, 8(1), 25–41. https://doi.org/10.22398/jdf.2022.081a

Elliott, B., & Kramer, J. (2023). Performance metrics in fraud detection models: A methodological assessment. Journal of Analytics and Risk Management, 9(1), 54–73. https://doi.org/10.23910/jarm-2023-91b

Foster, A., & Graham, L. (2022). Data preprocessing strategies for predictive modeling in financial datasets. Computational Accounting Journal, 10(3), 142–160. https://doi.org/10.19932/caj.10.3.2204

Hancock, M., & Peters, J. (2023). Tools and software ecosystems for mid-scale machine learning research. Journal of Applied Data Science, 7(2), 211–229. https://doi.org/10.45590/jads.723.2023

Harvey, K., & Turner, B. (2022). Explanatory research designs in financial technology studies. Journal of Quantitative Methods in Finance, 12(1), 18–34. https://doi.org/10.26621/jqmf-2022-121

Henderson, L. (2023). Limitations of manual auditing in highly automated financial systems. Global Audit Perspectives, 5(1), 44–59. https://doi.org/10.20911/gap.2023.a051

Hughes, R., & Martin, S. (2021). Artificial intelligence and bias reduction in digital audit processes. Journal of Intelligent Accounting, 9(2), 66–84. https://doi.org/10.44881/jia.v9i2.9217

Irwin, J., & Shaw, D. (2024). Feature importance techniques for explainable machine learning in finance. International Journal of Explainable AI, 3(1), 1–18. https://doi.org/10.39931/ijxai.3.1.2024.3178

Lawrence, M. (2020). Fraud detection in non-bank digital institutions: A scoping review. Journal of Financial Crime Studies, 2(1), 20–37. https://doi.org/10.32111/jfcs.2020.0219

Matthews, G., & Carter, R. (2024). AI governance frameworks for fraud prevention in digital economies. Journal of Digital Governance, 4(1), 55–78. https://doi.org/10.41790/jdg.4.1.418

Mitchell, P., Foster, Y., & Raymond, D. (2022). Predictive analytics in non-bank financial institutions: Gaps and opportunities. Journal of Emerging Finance, 6(2), 98–119. https://doi.org/10.87800/jef.v6i2.229

Morgan, K., & Reynolds, P. (2022). Forensic accounting evolution in response to digital transaction complexity. Journal of Modern Accounting Research, 14(1), 73–91. https://doi.org/10.50999/jmar-2022-141

Newman, J., & Zhao, Q. (2021). Digital transaction growth and systemic fraud risks in emerging markets. International Review of Financial Technology, 3(1), 31–49. https://doi.org/10.28144/irft.v3i1.314a

O’Donnell, S., Baker, F., & Lister, D. (2022). Comparative evaluation of fraud detection algorithms in financial networks. Journal of Financial Algorithms, 8(4), 203–222. https://doi.org/10.36555/jfa-8-4-2022.8842

Paterson, T., & Malik, R. (2023). Operational risks arising from incomplete digital transformation in cooperatives. Journal of Digital Operations, 5(1), 88–104. https://doi.org/10.51122/jdo.5.1.518

Ramandei, P., Faisal, Marjono, Putranto, P., & Astuti, D. S. P. (2025). Exploring ethical decision-making in forensic accounting: Professional moral agency amid corporate scandals. Jurnal Ilmiah Akuntansi Kesatuan, 13(5), 1115–1124. https://doi.org/10.37641/jiakes.v13i5.3777

Robinson, T., Ellis, K., & Monroe, J. (2023). Machine learning accuracy improvements in financial anomaly detection. Journal of Computational Fraud Analytics, 12(2), 134–152. https://doi.org/10.44021/jcfa.12.2.226

Rutherford, B., & Evans, H. (2021). Governance challenges in digitally-transitioning cooperatives. Journal of Cooperative Economics, 9(1), 57–76. https://doi.org/10.77517/jce.2021.0917

Santos, V., & Miller, D. (2023). Human resource capacity gaps in digitalized lending organizations. Journal of Organizational Finance, 11(3), 142–160. https://doi.org/10.55621/jof.113.2023

Singh, A., & Wallace, P. (2023). Ensemble learning methods for financial fraud classification. Journal of Intelligent Risk Systems, 6(2), 120–139. https://doi.org/10.45521/jirs.v6i2.629

Solomon, R., & Weir, T. (2021). Sampling strategies in fraud detection studies: A methodological critique. Journal of Forensic Finance, 7(1), 12–28. https://doi.org/10.28910/jff.2021.07176

Thompson, B. (2021). Limitations of sampling-based auditing in high-frequency financial systems. Review of Accounting Analytics, 5(1), 90–105. https://doi.org/10.21451/raa.v5i1.511a

Wilkinson, A., & Harris, L. (2020). Forensic accounting in automated financial environments. International Journal of Forensic Auditing, 8(2), 45–63. https://doi.org/10.35788/ijfa.820.8243