Open AccessAccuracy Invoked Course Recommender System using Collaborative Filtering
Author(s) -
A. K. Mariappan,
R.Ramana Surriyan,
E.S. Shobana
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.d9981.118419
Subject(s) - collaborative filtering , recommender system , computer science , selection (genetic algorithm) , field (mathematics) , sample (material) , test (biology) , course (navigation) , multimedia , information retrieval , artificial intelligence , paleontology , chemistry , physics , mathematics , chromatography , astronomy , biology , pure mathematics
It is always important that the student should choose the right course. The decision of taking the right course is very important as the student’s future depends on the course they opt to study. Most of the students are not much aware of the courses that are available in their own field of study. Selecting wrong courses might be due to the mismatch between the student’s aptitude, training and mental ability. Thus, the idea is to develop a system for helping the students to choose a course which would be best suited for him/her based on features like previous student selection, interest, languages known etc. Existing research has explored recommender system using content-based filtering but it can only do limited content analysis and the recommendation will not be precise at the end. An attempt is made to improve the performance of this system using Collaborative based filtering techniques which will recommend a ranked list of courses. Under Collaborative filtering techniques, user based collaborative filtering and item based collaborative filtering is used. Sample student datasets from Kaggle, has been used to test the performance of our system.