Enhancing Online Learning: A Comparative Analysis of Machine Learning Models and Data Visualization Techniques for Predicting Learner Flexibility

The fast growth of online learning has increased the demand for efficient tools and approaches to measure and improve student’s capacity to adapt to online learning. This paper gives a thorough comparative comparison of Machine Learning (ML) models and data visualization techniques for predicting the flexibility of learners in the realm of online education. In this study, various data visualization techniques are investigated to learn more about how learners behave, engage with, and perform in online courses. Understanding patterns and trends through data visualization is essential for educators and institutions to make well-informed decisions to enhance learner’s learning journeys. To find out how effective different visualization techniques are in revealing useful insights, IBM Cognos and Python are used. The suitability of several ML algorithms for predicting learners’ flexibility levels is also examined in this study. The predictive accuracy or mean accuracy score of several ML models, including XGBoost, Random Forests, CatBoost, Logistic Regression, and K Nearest Neighbour, is compared. The dataset used for this investigation contains a variety of learner-related variables, such as demographic data, past academic achievement, and interactions with online courses. For educators and educational institutions looking to use data-driven techniques to improve online learning experiences, the findings of this comparative study offer invaluable advice to them. This study contributes to the ongoing attempts to raise the caliber and efficacy of online education by identifying the most efficient data visualization strategies and ML models for forecasting learners’ flexibility. The study’s conclusions enable educators to proactively identify learners who are at risk of having difficulty with online learning, enabling prompt interventions and individualized support for academic success.