THE USE OF REGRESSION ANALYSIS IN AUDITING TO IDENTIFY TRENDS, CORRELATIONS, AND POTENTIAL FINANCIAL IRREGULARITIES

This study investigates the application of regression analysis in auditing to identify financial trends, correlations, and potential irregularities, addressing gaps in traditional auditing methods. Employing a descriptive research design, data was collected from peer-reviewed journals, industry reports, and case studies between 2020 and 2024. The regression analysis revealed a strong correlation between revenue and expense growth (r=0.92, p<0.01), with predictive models effectively identifying anomalies in financial reporting. Logistic regression models demonstrated increasing fraud detection rates from 10.0% in 2020 to 12.9% in 2024, while the chi-square test for financial misstatements indicated significant deviations (χ²=25.67, p<0.01). The findings confirm that regression analysis enhances audit effectiveness by improving fraud detection and financial oversight. The study recommends increased training for auditors in statistical methods, the integration of multiple analytical tools, improved data quality, consideration of macroeconomic factors, and the adoption of robust cyber security measures. These steps will ensure the effective use of regression analysis in modern auditing practices.