Abstract
In an increasingly complex and digitalized financial environment, the detection and prevention of corporate fraud and financial distress have become critical for investors, lenders, regulators, and corporate governance bodies. This study examines the integration of data analytics and forensic accounting to enhance fraud detection and insolvency prediction. Using a comprehensive case study of Bhushan Steel Limited (BSL), the research evaluates the effectiveness of the Altman Z-Score and Beneish M-Score models over a fifteen-year period (2012–13 to 2025–26). The findings indicate that the Altman Z-Score consistently identified financial distress and insolvency risk well before the company’s collapse, demonstrating strong predictive capability. In contrast, the Beneish M-Score detected earnings manipulation only during specific periods, reflecting limitations in identifying long-term structural deterioration. Statistical analysis further confirms the significance of both models in assessing financial reporting risks, although the Beneish framework exhibited greater variability. The study highlights the value of integrating traditional forensic accounting techniques with advanced data analytics and AI-driven systems to improve early warning mechanisms, strengthen corporate transparency, support informed decision-making, and enhance financial stability. The findings provide practical insights for regulators, financial institutions, auditors, and investors seeking proactive approaches to risk management and fraud prevention.
Keywords
Forensic AccountingData AnalyticsFinancial Fraud DetectionAltman Z-ScoreBeneish M-ScoreInsolvency PredictionFinancial Risk ManagementArtificial Intelligence
Cite this article
Dr. Prajakta Khule (2026). Enhancing Forensic Accounting with Data Analytics: An Empirical Study of Financial Risk Mitigation and Insolvency Prediction. International Innovations & Scholarly Trends Journal, 2(11), 286–299. https://doi.org/10.5281/zenodo.24272959
Share
Copyright & License
© 2026 — Authors retain the copyright of this article.
This is an open access article distributed under the
Creative Commons Attribution License (CC BY 4.0)
,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.