Session similarity based approach for alleviating cold-start session problem in e-commerce for Top-N recommendations

Research output: Chapter in Book/Report/Conference proceedingConference contribution

97 Downloads (Pure)

Abstract

Cold-start problem is one of the main challenges for the recommender systems. There are many methods developed for traditional recommender systems to alleviate the drawback of cold-start user and item problems. However, to the best of our knowledge, in session based recommender systems cold-start session problem still needs to be investigated. In this paper, we propose a session similarity-based method to alleviate drawback of cold-start sessions in e-commerce domain, in which there are no interacted items in the sessions that can help to identify users’ preferences. In the proposed method, product recommendations are given based on the most similar sessions that are found using session features such as session start time, location, etc. Computational
experiments on two real-world datasets show that when the proposed method applied, there is a significant improvement in the performance of recommender systems in terms of recall and precision metrics comparing to random recommendations for cold-start sessions.
Original languageEnglish
Title of host publicationProceedings of the 12th International Joint Conference on Knowledge Discovery
EditorsAna Fred, Joaquim Filipe
PublisherSciTePress
Number of pages8
Volume1
ISBN (Print)978-989-758-474-9
DOIs
Publication statusPublished - 12 Nov 2020
Event12th International Joint Conference on Knowledge Discovery -
Duration: 2 Nov 20204 Nov 2020
http://www.kdir.ic3k.org/

Conference

Conference12th International Joint Conference on Knowledge Discovery
Abbreviated titleKDIR
Period2/11/204/11/20
Internet address

Keywords

  • cold-start sessions
  • recommender systems
  • ession-based recommender systems
  • noissn

Fingerprint

Dive into the research topics of 'Session similarity based approach for alleviating cold-start session problem in e-commerce for Top-N recommendations'. Together they form a unique fingerprint.

Cite this