Information System Framework for Learners’ Dropout Prediction in Online Courses Using Machine Learning Algorithms

Authors

Neelam Naik, Assistant Professor, SVKM's Usha Pravin Gandhi College of Arts, Science and Commerce, IndiaFollow
Harshali Patil, Associate Professor, MET Institute of Computer Science, Mumbai, IndiaFollow
Seema Purohit, Professor Emeritus, B. K. Birla College of Arts, Science & Commerce (Autonomous), IndiaFollow

Abstract

The COVID-19 pandemic resulted in a slight pause in day-to-day activities in all areas. To streamline the activities during the pandemic, the contribution of the Information Technology (IT) sector was pervasive. IT played a vital role in the education domain, which led to welcoming the online teaching-learning process. As a part of curricula, Massive Open Online Courses (MOOC) have been introduced by many universities during and even after the pandemic. Online learning popularity has increased many folds in the world, but it faces the problem of retention and engagement of learners. The major problem in this system was related to the dropouts due to liberal learning environments and lack of learning pressure. The present study focuses on an information system framework for learners’ dropout prediction using footprints and evaluation data. Comparative analysis of five different datasets with learners’ diverse features is used for dropout prediction using various machine learning algorithms.

Recommended Citation

Naik, Neelam; Patil, Harshali; and Purohit, Seema, "Information System Framework for Learners’ Dropout Prediction in Online Courses Using Machine Learning Algorithms" (2023). ACIS 2023 Proceedings. 76.
https://aisel.aisnet.org/acis2023/76