Open AccessA proposed framework in an intelligent recommender system for the college student
Author(s) -
Dede Kurniadi,
Edi Abdurachman,
Harco Leslie Hendric Spits Warnars,
Wayan Suparta
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1402/6/066100
Subject(s) - recommender system , computer science , support vector machine , naive bayes classifier , process (computing) , cluster analysis , conceptual framework , association rule learning , artificial intelligence , machine learning , higher education , data science , mathematics education , knowledge management , psychology , philosophy , epistemology , political science , law , operating system
This article aims to proposed framework an Intelligent Recommender System (IRS) for students in higher education institutions. This conceptual framework includes problems in predicting student performance, the possibility of graduating on time, and recommends choosing subjects according to performance, and career interests, which are useful for assisting pedagogical interventions in future student development. The success in the development and implementation of the proposed IRS framework is inseparable from using data mining and machine learning techniques in predicting and providing recommendations. Data analysis consisted of clustering techniques, association rules, and classification using Support Vector Machine (SVM), Naïve Bayes, and k-Nearest Neighbour (k-NN). These techniques are used to solve problems related to students and to provide appropriate recommendations. The result is an IRS conceptual framework for the college student that can be used as smart agents to provide student guidance and suggestions to support the process of education in higher education.