Financial auditing has traditionally relied on sample-based testing and manual verification, but the rapid digitization of financial data has created wide datasets that require more advanced analytical techniques. The integration of machine learning (ML) and artificial intelligence (AI) is transforming auditing, allowing for real-time anomaly detection, risk assessment, and predictive analytics. KPI ratio correlation analysis plays a major role in this transformation, revealing hidden relationships between financial metrics and enabling auditors to detect fraud, inefficiencies, and financial misstatements before they escalate. The main purpose of the paper is to present that combining AI and ML methods enhances audit quality and trust in AI-driven financial assessments. Hybrid ML-AI methodologies are emerging as the most effective approach, balancing interpretability, accuracy, and regulatory compliance. Simple ML techniques, such as decision trees, provide transparency but struggle with complex patterns, whereas advanced AI models, including neural networks and Long short-term memory (LSTM) based architectures, offer superior predictive capabilities. The findings demonstrate that continuous auditing powered with ML-AI-driven approaches, enhances the monitoring of financial processes in real-time and improves overall risk management. Reducing the KPI set to uncorrelated indicators and integrating process mining with machine learning significantly improves model accuracy, stability, and anomaly detection capabilities.