The Impact of Machine Learning on Student Progress in Higher Education: A Case Study of Smaller City in Developing Countries

Main Article Content

Sadaf Shah, Amir Ali Mokhtarzadeh, Jefferson T. Banguando, Hera Naeem

Abstract

Using machine learning (ML) in customised learning systems has shown significant potential for improving student engagement and academic achievement in higher education. However, successfully scaling these individualised techniques remains a considerable issue, especially among huge student populations in underdeveloped countries. This study investigates the influence of (ML) on student advancement in a smaller city in a developing nation like Peshawar, Pakistan. We conducted a cross-sectional study at the University of Engineering and Technology Peshawar and surveyed 550 students enrolled in BS, MS, and PhD programs using a stratified random sampling technique. The data was collected using a standardised questionnaire, and the results were using correlation matrices, composite reliability, and regression models. The findings revealed substantial connections between ML applications and better educational outcomes, with the regression model accounting for 67% of the variation in enhanced tailored learning experiences. The remarkable representativeness of the model (R2=0.656) indicates that (ML) has a significant ability to improve institutional effectiveness and student learning. In addition, younger learners expressed tremendous enthusiasm for using ML in their teaching methods. The findings demonstrate machine learning's revolutionary potential in higher education, particularly in developing countries, by promoting cooperation, customised learning, and increased institutional efficiency.

Article Details

Section
Articles