MACHINE LEARNING–DRIVEN DECISION SUPPORT SYSTEMS FOR RESOURCE OPTIMIZATION AND CURRICULUM PLANNING IN ENGLISH DEPARTMENTS

Abstract

Managing resources and designing adaptive curricula in English departments has become increasingly complex due to fluctuating student enrollments, diverse course requirements, and evolving pedagogical demands. Traditional decision-making approaches often rely on static data and manual planning, leading to inefficiencies in faculty allocation, course scheduling, and curriculum relevance. This study proposes a Machine Learning (ML)–driven Decision Support System (DSS) to enhance resource management and curriculum planning in English departments. The system integrates multiple data sources, including historical enrollment records, student performance metrics, course feedback, and faculty workload data. Various ML models are employed, such as regression techniques for enrollment forecasting, classification algorithms for predicting student success, and clustering methods for identifying patterns in course demand. Additionally, recommendation algorithms are utilized to support dynamic curriculum development and elective course selection. The proposed approach is expected to improve decision-making accuracy, optimize resource utilization, and enable data-driven curriculum adjustments aligned with student needs and institutional goals. Preliminary findings suggest that ML-based DSS can significantly reduce planning inefficiencies while enhancing responsiveness to academic trends. The implications of this research extend to academic institutions seeking to modernize departmental management practices. By integrating intelligent systems into administrative processes, English departments can achieve greater operational efficiency, improve teaching outcomes, and foster a more adaptive and student-centered learning environment.