Educational data mining is an emerging discipline that focuses on development of self-learning and adaptive methods. It is used for finding hidden patterns or intrinsic structures of educational data. In the field of education, the heterogeneous data is involved and continuously growing in the paradigm of big data. To extract meaningful knowledge adaptively from big educational data, some specific data mining techniques are needed. This paper presents a personalized e-learning system architecture which detects and responds teaching contents according to the students’ learning capabilities. Furthermore, the clustering approach is also presented to partition the students into different groups based on their learning behavior. The primary objective includes the discovery of optimal settings, in which learners can improve their learning capabilities to boost up their outcomes. Moreover, the administration can find essential hidden patterns to bring the effective reforms in the existing system. The various clustering methods K-means, Clustering by Fast Search and Finding of Density Peaks (CFSFDP), and CFSFDP via Heat Diffusion (CFSFDP-HD) are also analyzed using educational data mining. It is observed that more robust results can be achieved by the replacement of K-means with CFSFDP and CFSFDP-HD. The proposed e-learning system using data mining techniques is vigorous compared to typical e-learning systems. The data mining techniques are equally effective to analyze the big data to make education systems robust.
Adjusting Felder-Silverman learning styles model for application in adaptive e-learning