<![CDATA[Production planning is a critical manufacturing function that requires balancing production targets, equipment availability, workforce capacity, and material expenditure under continuously changing operational conditions. Artificial intelligence (AI)-based decision support systems (DSS) have emerged as promising tools for improving planning accuracy and resource allocation by enabling data-driven production decisions. This study presents a descriptive evaluation of production performance and departmental resource allocation before and after the implementation of an AI-based DSS in a manufacturing facility in Aceh, Indonesia. A before-and-after research design was applied using 24 monthly production records, comprising 12 months of conventional planning in 2023 and 12 months of AI-supported planning in 2024. The analysis compares key operational indicators, including production targets, realized output, production achievement, machine utilization, workforce allocation, raw material costs, departmental allocation shares, and operational efficiency. Results indicate that mean realized production increased from 812.25 tons to 984.67 tons per month, while the average production achievement rate improved from 83.96% to 95.89%. Mean machine utilization increased from 69.92% to 87.49%, reflecting more effective use of manufacturing resources. At the same time, average monthly raw material expenditure decreased from IDR 575.91 million to IDR 548.09 million, indicating improved cost efficiency. Across seven production departments, mean operational efficiency increased by 18.51 percentage points, rising from 69.05% to 87.56% after AI-based DSS implementation. Because the comparison is based on two consecutive calendar years without a parallel control facility or randomized intervention, the findings should be interpreted as descriptive operational evidence rather than causal proof of AI effectiveness. This study contributes a practical evaluation framework for assessing AI-supported production planning by integrating production performance, resource utilization, cost efficiency, and departmental allocation into a comprehensive decision-support model for continuous improvement in manufacturing operations]]>
Copyrights © 2023
