Please use this identifier to cite or link to this item:
Author(s): Ana Isabel Neves Alves de Sousa
Title: Market-based Higher Education Course Recommendation
Issue Date: 2016-07-08
Abstract: The choice of a higher education program is determinant in the future career. This choice needs to take into account several aspects, such as its future employability, if it provides the competences required for a desired job, as well as whether its scope of depth and breath fits the needs of the student. Having this is mind, it is worth to invest the time to make a better informed decision. Since alumni represent the most trusted source of information about the paths a certain degree confers access to, we propose a recommendation system based on alumni data to solve this problem.Using the information about the alumni and job offers, we aim to find out how to use it in order to recommend the most appropriate higher education programs to achieve a certain job. The recommender system will have as input the user's desired career and, by making a match between the competences required for that career and the competences that a program provides to their students, it will output a ranking of higher education programs to take.Since this goal fits into the recommender systems category, we present an overview on the state of the art of this research area, with special focus on collaborative filtering methods and evaluation of recommendation tasks. We then describe the solution for the problem proposed, in terms of data set construction and analysis, similarity measure choice and implementation details of user and item based recommendations.
Description: -
Subject: Engenharia electrotécnica, electrónica e informática
Electrical engineering, Electronic engineering, Information engineering
Call Number: 141381
Document Type: Dissertação
Rights: openAccess
Appears in Collections:FEUP - Dissertação

Files in This Item:
File Description SizeFormat 
141381.pdfMarket-based Higher Education Course Recommendation4.14 MBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons