HOW PREDICTIVE STATISTICAL MODELS ARE REVOLUTIONIZING RISK-BASED AUDITING PRACTICES ACROSS INDUSTRIES

This study investigates how predictive statistical models revolutionize risk-based auditing practices across industries by enhancing accuracy, efficiency, and fraud detection capabilities. Using a mixed-methods approach, statistical techniques such as chi-square tests, ANOVA, and regression analysis were applied to assess model effectiveness. Findings indicate that predictive analytics increased risk assessment accuracy by 20% on average from 2020 to 2024, with financial services showing a 28.6% improvement. Audit time reduced by 40%, and regression analysis confirmed a strong correlation (R² = 0.89) between investment in predictive models and audit accuracy enhancement. The overall Pearson correlation coefficient (r = 0.92, p < 0.001) validates the significant impact of predictive models on auditing efficiency. Despite these benefits, challenges such as data privacy concerns, algorithmic biases, and resistance to AI adoption persist. The study recommends robust data governance, industry-specific model customization, and auditor training to maximize predictive auditing benefits while ensuring compliance and ethical AI use.