<![CDATA[Indonesia's transition from the SPBE evaluation framework to the 2025–2029 Pemdi (Digital Government) Index marks a strategic shift toward comprehensive governance maturity. However, regional governments face significant challenges in strategic planning due to the absence of empirical models linking historical SPBE performance to future Pemdi trajectories and a lack of data-driven guidance for prioritizing governance interventions. This research aims to develop an integrated Classification-Prediction-Prescription (CPP) framework to classify, forecast, and prescribe regional digital government governance maturity levels. The proposed methodology employs machine learning algorithms (Random Forest and Gradient Boosting) to conduct multi-class classification (five maturity levels) and regression (continuous score prediction) using longitudinal SPBE data (2019–2024) from 548 Indonesian regional governments. This quantitative approach is complemented by feature importance analysis and scenario-based simulations to generate actionable insights. The models are projected to achieve over 85% classification accuracy and a regression RMSE of under 0.5. The synthesis of main findings reveals that indicators within the policy and architecture planning domains are the strongest predictors driving maturity progression. Furthermore, the study segments regional governments into four distinct trajectory clusters and formulates a tailored prescriptive recommendation matrix across multiple planning horizons. In conclusion, the CPP framework effectively translates national evaluation data into actionable intelligence, empowering regional governments to optimize resource allocation, prioritize high-impact interventions, and systematically align their digital transformation pathways with formal planning documents such as the RPJMD and Regional Action Plans.]]>
Copyrights © 2026
