Prediction of Lecturer Performance using Machine Learning Techniques

Abstract

Recent advances in artificial intelligence techniques, including machine learning models, have led to the expansion of practical prediction capabilities in various fields. One of the major challenges facing higher education institutions is the amount of data being accumulated and how to use that data to improve the quality of academic programs. The quality of lecturers' activities mainly affects the quality of educational services in higher education institutions. In this article, a dataset collected from the Course Evaluation Survey repository of the Management and Science University is used to predict lecturer performance. To determine lecturers' effectiveness in the higher education system, a group of machine learning algorithms were applied to predict the performance of lecturers in the higher education system. Our research on lecturer performance could contribute to a holistic understanding of factors influencing educational outcomes and predicting student success, and dropout rates. Lecturer performance can influence student satisfaction, motivation, and overall academic experience. High-quality teaching can contribute to a positive learning environment, implement targeted interventions to address potential issues, and create a more supportive learning environment.