Optimizing audit processes through open innovation: Leveraging emerging technologies for enhanced accuracy and efficiency

Abstract

Artificial intelligence (AI) and machine learning (ML) are reshaping financial auditing by enabling greater efficiency, precision, and risk detection. Leveraging the U.S. Securities and Exchange Commission (SEC) Financial Statement Data Sets for the fiscal year 2024, a dual-model framework combining supervised and unsupervised ML techniques is applied. Using Random Forest and K-Means algorithms, the analysis processes over 14 million records to classify filing risks and detect anomalies across 399 industries. The models achieved a 95.7 % accuracy rate in identifying low-risk filings, with clustering insights revealing distinct behavioral profiles among reporting entities. A stable reporting environment with low volatility further supports reliable audit automation. Beyond AI/ML, the research examines the potential of blockchain for decentralized auditing, IoT for real-time asset tracking, and cloud infrastructure for shared audit ecosystems. By integrating these emerging technologies within an open innovation paradigm, the framework delivers a scalable and practical path toward audit modernization. The results offer actionable insights for auditors, regulators, and stakeholders aiming to strengthen oversight through intelligent, data-driven practices.