Please use this identifier to cite or link to this item:
Title: Forgetting Methods for Incremental Matrix Factorization in Recommender Systems
Authors: Matuszyk,P
João Marques Silva
Alípio Jorge
João Gama
Issue Date: 2015
Abstract: Numerous stream mining algorithms are equipped with forgetting mechanisms, such as sliding windows or fading factors, to make them adaptive to changes. In recommender systems those techniques have not been investigated thoroughly despite the very volatile nature of users' preferences that they deal with. We developed five new forgetting techniques for incremental matrix factorization in recommender systems. We show on eight datasets that our techniques improve the predictive power of recommender systems. Experiments with both explicit rating feedback and positive-only feedback confirm our findings showing that forgetting information is beneficial despite the extreme data sparsity that recommender systems struggle with. Improvement through forgetting also proves that users' preferences are subject to concept drift.
metadata.dc.type: conferenceObject
Appears in Collections:LIAAD - Articles in International Conferences

Files in This Item:
File SizeFormat 
P-00G-PQN.pdf497.02 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.