A big data architecture for learning analytics in higher education

Abstract

Data with high volume, velocity, variety and veracity brings the new experience curve of analytics. Big data in higher education comes from different sources that include blogs, social networks, student information systems, learning management systems, research, and other machine-generated data. Once the data is analysed it promises better student placement processes; more accurate enrolment forecasts, and early warning systems that identify and assist students at-risk of failing or dropping out. Big data is becoming a key to creating competitive advantages in higher education. Like with any organization, traditional data processing and analysis of structured and unstructured data using RDBMS and data warehousing no longer satisfy big data challenges. The lack of adequate conceptual architectures for big data tailored for institutions of higher education has led to many failures to produce meaningful, accessible, and timely information for decision making. Therefore, this calls for the development of conceptual architectures for big data in higher education. This paper presents an architecture for big data analytics in higher education.