An Effective Learning Management System for Revealing Student Performance Attributes

A learning management system (LMS) streamlines the teaching process in a centralized place, recording, tracking, and reporting the delivery of educational courses and student performance. Educational knowledge discovery from such e-learning systems plays a crucial role in rule regulation, policy establishment, and system development. However, existing LMSs do not have embedded mining modules to directly extract knowledge. As educational modes become more complex, educational data mining efficiency from those heterogeneous learning behaviours is gradually degraded. Accordingly, this study proposes an effective LMS which processes the stored data through an advanced educational data mining module. The mining module utilizes probability-based frequent pattern mining for generating candidate itemsets and updating the LMS database in each iteration for complexity reduction. The conditional probability in-crement ratio (CPIR) is deployed as an exceptionality measure to mine common and exception rules simultaneously. The iteratively generated rules can reveal academic performance patterns which have merits in learning personal goal achievement. Experimental results demonstrate three times increased mining efficiency of the proposed module without information loss. The design of the LMS enables educators to learn from past experiences, empowering to guide and intervene with students in time, provide valuable insights in helping plan effective learning pedagogies, improve curriculum design, guarantee quality of teaching, and eventually improve students academic success.