DATA-DRIVEN DECISION-MAKING IN AUDIT PLANNING: A PREDICTIVE ANALYTICS APPROACH

Abstract

This article examines the methodological foundations of applying predictive analytics in audit planning within the digital economy. It highlights the role of data-driven approaches in improving audit efficiency, accuracy, and decision-making. The study compares the traditional Audit Risk Model (ARM) with the concept of Intelligent Audit Transformation (IAT), emphasizing their key differences and practical implications. Particular attention is given to the use of machine learning in risk assessment and anomaly detection. The paper also analyzes the current state of audit digitalization in Uzbekistan and identifies key challenges and opportunities. The findings indicate that predictive analytics transforms audit planning from a reactive to a proactive, data-driven process.