A Novel Method for Performance Measurement of Public Educational Institutions Using Machine Learning Models

Lack of education is a major concern in underdeveloped countries because it leads to poor human and economic development. The level public institutions varies across all regions around the globe. Current disparities access worldwide are mostly due systemic regional differences distribution resources. Previous research focused on evaluating students’ academic performance, but less has been done measure performance educational institutions. Key indicators for evaluation institutional differ from student indicators. There dire need evaluate institutions’ based their results large scale. This study proposes model key through data mining techniques. Various feature selection methods were used extract Several machine learning models, namely, J48 decision tree, support vector machines, random forest, rotation artificial neural networks employed build an efficient model. different factors, i.e., number schools specific region, teachers, school locations, enrolment, availability necessary facilities that contribute performance. It was also observed urban performed well compared rural improved showed outperformed other models achieved accuracy 82.9% when relief-F method used. will help efforts governance monitoring, policy formulation, target-setting, evaluation, reform address issues challenges worldwide.