A Random Forest-Based AI Decision Support System for an Integrated Indonesian Civil Service Information System

Digital transformation in public administration increases the need for personnel information systems that can consolidate fragmented civil-service records and turn them into timely, transparent, and actionable decision support. This study developed SIPINTAR (Integrated, Adaptive, and Responsive Interactive Personnel Intelligence System), an artificial intelligence-based platform designed to integrate civil-service personnel information and support administrative decision-making within an Indonesian government institution. The study adopted a Research and Development approach and implemented the system through a Waterfall-based Software Development Life Cycle. Personnel data from multiple source systems, representing 5,320 civil servants and more than 42,000 historical records for 2019–2025, were integrated using Application Programming Interfaces (APIs) and Extract, Transform, and Load (ETL) processes. The integrated data were then subjected to cleaning, transformation, feature engineering, and Random Forest modeling. Model performance was assessed using accuracy, precision, recall, and F1-score, whereas system acceptance was examined through a User Acceptance Test. The strongest reported result was obtained for employee-performance prediction, with 87.24% accuracy, 86% precision, 85% recall, and 85.5% F1-score. Feature-importance analysis as the explainable artificial intelligence component identified performance score, competency level, and years of service as the three most influential variables. The integrated dashboard and AI Assistant provided consolidated access to analytical information, and the UAT result reached 91.40%. Overall, the findings suggest that SIPINTAR can move personnel information management beyond historical record keeping toward predictive and explainable decision support. Nevertheless, the results should be validated with baseline models and broader institutional datasets before being generalized across agencies.