Narges Majidi
M.Sc. Thesis Proposal
Supervisor: Dr. Wolfgang Banzhaf

A Personalized Course Recommendation System Based on Career Goals

Department of Computer Science
Thursday, January 28, 2016, 2:40 p.m., Room EN 2022

---

Abstract

Recommender systems have become very popular and are integrated into many applications that we use everyday. We are recommended music pieces, articles, books, movies and many other things of daily life by many websites. Education is another example of a domain where recommender systems can help make better and wiser decision that affect the future. With the growing number of available courses online, it is a serious problem of how to choose the right courses. In this thesis, a new recommendation
system for courses is proposed that takes the user’s career goals into consideration in order to help them with choosing the right path toward their goals. The system will use the data from LinkedIn professional social network. Public profiles of people with desired career goals and their top skills will be extracted in order to form the data set. Then with the use of association rule mining and genetic algorithm, best rules will be evolved in order to show which skills are necessary for each career goal. Then with the use of a set of data extracted from course descriptions, a table will be generated showing the associations between skills and courses. With the use of the extracted data set from LinkedIn, associations between each skill and courses, and a minimization algorithm for finding minimum number of effective courses, the system will hopefully be able to recommend courses to the users in order to help users achieve their career targets faster.

 

Narges Majidi
M.Sc. Candidate
Supervisor: Dr. Wolfgang Banzhaf

A Personalized Course Recommendation System
Based on Career Goals

Department of Computer Science
Wednesday, December 20, 2017, 10:00 a.m., Room EN 2022

---

Abstract

Recommender systems have become very popular and are integrated into many applications that we use everyday. We are recommended music pieces, articles, books, and movies bymanywebsites and devices in our everyday life. Education is another example of a domain where recommender systems
can help make better and wiser decisions that can affect someone's future. With the growing number of available online courses, it is a serious problem of how to choose the right courses. In this research, a proof of concept of a course recommender system is proposed that takes the users career goals into consideration in orderto help them with choosing the right path toward their desired future job. To this end, a hybrid approach is proposed: 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 the 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 next 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, the last phase of the method runs another Genetic Algorithm on the course dataset in order to find the optimum set of courses. We show that the courses that are being suggested to users with a specific career goal in mind will prepare them to compete well by adding key skills that are trending on the market among many employers.