Research on the Application of Big Data Technology in Internal Audit of Bank Credit Operations

Amid intensified financial risk regulation, traditional credit audit models struggle with high-frequency, high-dimensional, and heterogeneous data, highlighting the need for intelligent transformation. This paper explores the application of big data in bank credit internal audits, proposing a system framework that integrates distributed processing, feature engineering, and machine/deep learning for risk identification. An intelligent audit platform with real-time computing and visualization is developed. Experimental results demonstrate superior performance over traditional methods in anomaly detection accuracy, response efficiency, and resource utilization, offering practical insights for building a transparent and efficient credit audit system.