Machine Learning for Public Sector Performance Prediction: The Role of Communication, Decision-Making, and Strategy Alignment

Aris Riyadi (Padjadjaran University)
Engkus Kuswarno (Padjadjaran University)
Dadang Sugiana (Padjadjaran University)
Asep Suryana (Padjadjaran University)

Journal of Applied Engineering and Technological Science (JAETS)
Vol. 7 No. 2 (2026): Journal of Applied Engineering and Technological Science (JAETS)

This study explores the relationship between communication quality, participatory decision-making, and organizational performance in the public sector using machine learning techniques. Data were collected from government agencies, employing stratified random sampling to survey civil servants at various levels of tenure. A decision-tree classification model was used to identify key predictors of organizational performance, with the model achieving 71% accuracy and a weighted F1-score of 0.71. The results highlight that interpersonal communication quality, employee involvement in decision-making, and strategic alignment were the most significant factors influencing performance. This study demonstrates the value of machine learning in capturing complex, nonlinear relationships in organizational data and provides practical insights for enhancing communication systems and decision-making structures in public institutions. The findings offer a framework for improving public sector performance by promoting participatory governance and aligning strategic priorities.