Sequential Rule Mining on the Student Behavior Data of an E-Learning Platform in the Field of Financial Sciences: Case Study

Abstract

Today, we observe that innovative technologies are needed to increase students' success on e-learning platforms. There is a need to develop a system that monitors students' activities, identifies common repetitive behaviors, and makes suggestions. Within the scope of this research, we perform sequential rule mining on sequential action sequences. We introduce a software architecture, which mines the most repetitive sequential action sequences and enables rules based on these sequences. To demonstrate the usability of the proposed method, we develop a prototype application for an e-learning platform that provides training in financial sciences. We carry out tests on the developed prototype application in terms of performance and scalability. The results reveal that the proposed software architecture successfully extracts rules from sequential action sequences obtained from student behavior data.