Abstract
The Role of Data Mining, Machine Learning, Artificial Intelligence, and Digital Forensic in Indonesian Public-Sector Fraud Detection in the Indonesian public-sector audit environment. The study aims to evaluate whether advanced analytical technologies improve auditors’ effectiveness in detecting fraudulent financial reporting and whether Digital Forensic strengthens or weakens the relationships between these technologies and fraud detection performance. This study employed a causal associative quantitative approach using primary data collected through questionnaires distributed to auditors at the Financial and Development Supervisory Agency (BPKP) representative offices across Sumatra, Indonesia. The population consisted of 290 auditors, and the sample was selected using a simple random sampling technique based on the Slovin formula. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with SmartPLS 4. The analysis included outer model evaluation, inner model assessment, hypothesis testing, and moderation analysis. The results indicate that Data Mining has a significant positive effect on Financial Statement Fraud Detection. In contrast, Machine Learning and Artificial Intelligence do not significantly influence fraud detection effectiveness. Furthermore, Digital Forensic does not strengthen the relationships between Data Mining, Machine Learning, Artificial Intelligence, and fraud detection. Instead, the moderating effects of Digital Forensic tend to weaken these relationships within the current audit environment. The structural model demonstrates satisfactory explanatory and predictive capability in explaining variations in fraud detection performance.