Machine Learning and Analytics for Performance Prediction of ODL Students: Decoding Digital Communication for Sustainability

Abstract

Aim of the Study: The extensive use of digital communication in Open and Distance Learning (ODL) is generating a huge volume of academic transactions. This occurs through online platforms such as the Learning Management System (LMS) and Student Information System (SIS). The goldmine LMS and SIS transactions emphasized the need to convert this data into meaningful knowledge. The aim of the current study is to apply machine learning and analytics to decode the digital data generated by LMS and SIS, extracting meaningful knowledge for continuous improvement and sustainability in educational processes.

Methodology: This paper presents a model based on learning analytics and machine learning to predict the academic performance of students enrolled in a course offered at an open university of Pakistan. The researchers’ extracted data for two semesters combined it with the best attribute subset and employed eight (08) machine learning algorithms by dividing data into four sets.

Findings: The results of the study validated the predictive ability of machine learning on a localized dataset of distant learners of the country’s largest open university. Students use digital platforms for communication and learning and their usage can be analyzed to decode and predict their performance. The findings of the study demonstrate the effective utilization of Artificial Intelligence and Machine Learning technologies, effectively overcoming challenges and leveraging them to create opportunities.

Conclusion: It is concluded from the study that students use digital platforms for communication and learning, and their usage can be analysed to decode and predict their performance.