Abstract
As online education expands, a substantial amount of data is generated by the interactions, behaviours, and learning outcomes of students. To improve online education, this research looks at how this data may be examined using big data techniques. By examining patterns in data such as student engagement, material usage, and performance, we can identify trends, predict student success, and customise learning experiences. The rapid expansion of online learning platforms has generated an enormous amount of data, which presents opportunities for research and the extraction of crucial insights for enhancing institutional initiatives and educational experiences. This study explores the use of big data techniques for the extraction and analysis of educational data from online learning environments. We examine how to identify trends, predict student progress, and improve instructional materials using large datasets including user behaviour, engagement patterns, content interaction, and performance measures. The study highlights several data mining techniques, such as clustering, classification, and recommendation systems, to improve the personalisation of learning experiences and assist educators in making evidence-based decisions. Finally, we offer a framework that allows educational platforms to adapt to student demands by utilising analytics and machine learning to support choices in real time. This study aims to show how big data can revolutionise the way that education is delivered and help companies improve online learning. Online education is the result of combining traditional classroom instruction with internet technologies. Lately, it has been expanding rapidly. Big data’s speed, diversity, affordability, and magnitude are having a significant impact on and reshaping online education. Research on educational technology that aligns with big data analysis, as well as an examination of the development trend and legality of online education, can help achieve a tailored development strategy that makes use of the promoted educational technology and big data-based educational thinking.

DIP: 18.02.1017/20261101
DOI: 10.25215/2455/11011017