Novel Framework for Quality Retention on Educational Big Data

Abstract

Adoption of big data concept towards managing increasing data from the educational sector will have various benefits in terms of knowledge sharing process. The existing research approaches towards managing educational data in terms of high end analytics is either missing or is quite narrowed that doesn’t encapsulate the concept of big data implementation with practical problem. Therefore, this paper presents a discussion of a distributed framework that is capable of performing transformation of raw educational data arriving from distributed sources followed by applying a novel mining approach in order to ensure the final data with highest quality. The term quality interprets as a dynamic educational big data to be highly structured and free from any form of artifacts. Result analysis shows that proposed system offer faster transformation time and better data purity over synthetic educational big data.