Item-Item Collaborative Filtering via Graph Regularization

Bachelor Thesis (2022)
Author(s)

M.M.M. Koper ook geschreven Jansen (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Elvin Isufi – Mentor (TU Delft - Multimedia Computing)

Maosheng Yang – Mentor (TU Delft - Multimedia Computing)

A. Zarras – Graduation committee member (TU Delft - Cyber Security)

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2022 Melle Koper ook geschreven Jansen
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 Melle Koper ook geschreven Jansen
Graduation Date
22-06-2022
Awarding Institution
Delft University of Technology
Project
['CSE3000 Research Project']
Programme
['Computer Science and Engineering']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

A recommendation algorithm aims to predict the quality of a user's future interaction with certain items based on their previous interactions. As research progresses, these algorithms are becoming increasingly more complicated with the use of machine learning and neural networks. This paper looks into a more simple solution. The recommendation domain can be represented as a graph, meaning different graph regularization techniques can be used to solve the same problem. After running experiments comparing the Item-Item Tikhonov Regularizer and the Sobolev Regularizer to a baseline, the item-item standard Collaborative Filtering method, it is clear that the Graph Regularization techniques outperform the baseline. Given that it has been shown that Collaborative Filtering is a relatively competitive method in this field, outperforming it means that Graph Regularizers are a viable and potentially competitive method for solving the recommender problem.

Files

Research_Paper_6_1.pdf
(pdf | 0.627 Mb)
License info not available