A personalized course recommendation system based on career goals

Majidi, Narges (2018) A personalized course recommendation system based on career goals. Masters thesis, Memorial University of Newfoundland.

[img] [English] PDF - Accepted Version
Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.

Download (1MB)


Recommendation systems have become very popular and are integrated into many applications that we use everyday. We are recommended music pieces, articles, books, and movies by many websites and devices in our everyday life. Education is another example of a domain where recommendation systems can help make better and wiser decisions that can affect someone's future. With the growing number of available online courses, it is difficult to choose the right courses. In this thesis, a proof-of-concept of a course recommendation system is proposed that takes the users' career goals into consideration in order to help them with choosing the right path toward their desired future job. First, data is extracted from Indeed job postings for the desired job titles showing the relations between job titles and skills. Then, a second dataset is gathered which contains a set of available online courses and the skills that they cover. The first phase of the method generates some association rules using the Apriori algorithm which is then used in the second phase that runs a Genetic Algorithm to find the best set of skills for each career goal. After finding the best set of skills for a desired career goal, we need to find the minimum number of courses that can cover all of these skills to be able to recommend them to users which is an instance of the Set Cover problem. In our method, the last phase runs another Genetic Algorithm on the course dataset in order to find the optimum set of courses. This proof-of-concept approach demonstrates that courses that are suggested to users with a specific career goal add key skills that are trending in the market to their list of qualifications.

Item Type: Thesis (Masters)
URI: http://research.library.mun.ca/id/eprint/13339
Item ID: 13339
Additional Information: Includes bibliographical references (pages 85-96).
Keywords: Recommendation System, Genetic Algorithm, Association Rule Mining, E-Learning
Department(s): Science, Faculty of > Computer Science
Date: April 2018
Date Type: Submission
Library of Congress Subject Heading: Recommender systems (Information filtering); Internet in education--Computer programs; Vocational guidance--Computer programs; Genetic algorithms

Actions (login required)

View Item View Item


Downloads per month over the past year

View more statistics