EVALUATING THE EFFECTIVENESS OF ONLINE LEARNING PLATFORMS FOR SELF-EDUCATION

The increasing reliance on online learning platforms has redefined how individuals pursue education, particularly in self-directed environments. These platforms, including Coursera, edX, Udemy, and LinkedIn Learning, provide learners with flexible access to diverse educational content. However, their rapid expansion has raised critical questions regarding their true effectiveness in fostering deep learning, engagement, knowledge retention, and career applicability. While online learning offers undeniable advantages in terms of accessibility and scalability, challenges such as low completion rates, limited peer interaction, and insufficient instructional support persist. This study aims to evaluate the effectiveness of online learning platforms for self-education, focusing on user experiences and learning outcomes. The research employs a mixed-methods approach that integrates quantitative data from structured questionnaires and qualitative feedback from open-ended responses. A survey was distributed to a sample of undergraduate learners with varied exposure to online platforms. Responses were analyzed using Power BI for descriptive and inferential statistics, while advanced machine learning techniques such as K-Means clustering and Random Forest classifiers were used to identify behavioral patterns and key predictors of learner confidence and success. The results reveal that most learners exhibit moderate to high confidence in using online platforms for independent learning, with notable appreciation for platform usability, content relevance, and resource availability. However, the analysis also highlighted common challenges, including inadequate peer collaboration, inconsistent instructor engagement, and underdeveloped goal-setting habits. Clustering analysis segmented learners into distinct groups based on engagement and satisfaction, while predictive modeling confirmed that content satisfaction, platform usability, and clear learning goals are critical to positive learning outcomes. This research contributes to the broader understanding of online learning by providing a robust, data-driven framework for evaluating platform effectiveness in self-education contexts. The integration of machine learning with traditional survey analysis offers a more nuanced view of learner behavior, enabling targeted recommendations for platform developers, instructional designers, and educators. By identifying both the strengths and limitations of current online learning models, this study supports the development of more personalized, engaging, and outcomes-oriented digital learning environments. Keywords: Online Learning Platforms, Self-Education, Learner Engagement, Machine Learning, Educational Technology