An intelligent recommendation framework for student counselling management in Thai private universities
Kongsakun, Kanokwan (2013) An intelligent recommendation framework for student counselling management in Thai private universities. Professional Doctorate thesis, Murdoch University.
This study proposed a framework for an Intelligent Recommendation System for private universities in Thailand. Choosing a program of study for students is significant due to the commitment involved and the potential career opportunities. However, many students have enrolled in course majors without receiving any advice from appropriate authorities or university services. This could have potential mismatch between a student’s background, personal interests and capability, with the particular course being taken up. This may lead to low retention and dropouts. In order to improve the academic management processes, many universities are developing innovative information systems and services with an aim to enhance efficiency and student relationship. One of the key initiatives is the development of Student Relationship Management Systems (SRM) and among their functions, is the provision of recommendation and advice for students. The proposed system in this study examined the correlation between up to 11,000 student records and their academic performance. The system focuses on the following outcomes: programme and activity recommendation, likely overall GPA and results in each year, Identification of postgraduate students and potential dropouts. Association Rules and K-Means Clustering have been used together with three classification techniques: Artificial Neural Networks (ANN), Decision Tree (DT) and Support Vector Machines (SVM). Ensemble and the Modular Artificial Neural Networks based on Optimised Weight of Subspace Reconstruction (MANN-OWSR) have also been used to combine the learning models for improved performance. Results from the experiments will be useful for counsellors and academic staff in suggesting appropriate recommendations for the students.
|Publication Type:||Thesis (Professional Doctorate)|
|Murdoch Affiliation:||School of Engineering and Information Technology|
|Item Control Page|
Downloads per month over past year