An Adaptive Educational Data Mining Technique for Mining Educational Data Models in Elearning Systems

Background/Objectives: After a deep survey carried out by the National data premises with stats which reveals that the insufficient models which are existing in the real world scenario for modelling the data values in educational CMS, educational websites etc. are insufficient. In this paper a new adaptive data mining techniques is used to model the educational data using the DM classifiers. Methods/Statistical analysis: A deep study and interactive graphical representation for e-commerce in educational system has been defined in a refined view. Here the proposed data model using advanced classifier introduces a new agent based intelligent system which construct the data model in form of 3D cubes for every classification. For example, the classifier classifies the data model with subject to tutor, faculty, students, syllabi, academia orientation. Findings: The parameter mentioned is modelled in the cubical view. These cubical data model are given as the inbound inputs to the processing tools like OLAP, OPAC. Experimental results in the form of data model are demonstrated in the result section. During the experiment, the data's are read into the matrix and then processed. Applications/Improvements: Finally the cubic model can be used to any short of modelling techniques which supports all the relational models, logical models and physical models, whereas the proposed model has been demonstrated as the result for the selective datasets and has not been tested with any universal data mining DB's.