Simple and effective neural-free soft-cluster embeddings for item cold-start recommendations

<p>Recommender systems are widely used in online platforms for easy exploration of personalized content. The best available recommendation algorithms are based on using the observed preference information among collaborating entities. A significant challenge in recommender system continues to...

Full description

Saved in:
Bibliographic Details
Main Author: Shameem A. Puthiya Parambath (14150997) (author)
Other Authors: Sanjay Chawla (4254202) (author)
Published: 2022
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513567907119104
author Shameem A. Puthiya Parambath (14150997)
author2 Sanjay Chawla (4254202)
author2_role author
author_facet Shameem A. Puthiya Parambath (14150997)
Sanjay Chawla (4254202)
author_role author
dc.creator.none.fl_str_mv Shameem A. Puthiya Parambath (14150997)
Sanjay Chawla (4254202)
dc.date.none.fl_str_mv 2022-11-22T21:13:05Z
dc.identifier.none.fl_str_mv 10.1007/s10618-020-00708-6
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Simple_and_effective_neural-free_soft-cluster_embeddings_for_item_cold-start_recommendations/21597222
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Applied computing
Data management and data science
Distributed computing and systems software
Recommender systems
Item recommendation
Item cold-start problem
Soft-cluster embeddings
dc.title.none.fl_str_mv Simple and effective neural-free soft-cluster embeddings for item cold-start recommendations
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Recommender systems are widely used in online platforms for easy exploration of personalized content. The best available recommendation algorithms are based on using the observed preference information among collaborating entities. A significant challenge in recommender system continues to be item cold-start recommendation: how to effectively recommend items with no observed or past preference information. Here we propose a two-stage algorithm based on soft clustering to provide an efficient solution to this problem. The crux of our approach lies in representing the items as soft-cluster embeddings in the space spanned by the side-information associated with the items. Though many item embedding approaches have been proposed for item cold-start recommendations in the past—and simple as they might appear—to the best of our knowledge, the approach based on soft-cluster embeddings has not been proposed in the research literature. Our experimental results on four benchmark datasets conclusively demonstrate that the proposed algorithm makes accurate recommendations in item cold-start settings compared to the state-of-the-art algorithms according to commonly used ranking metrics like Normalized Discounted Cumulative Gain (NDCG) and Mean Average Precision (MAP). The performance of our proposed algorithm on the MovieLens 20M dataset clearly demonstrates the scalability aspect of our algorithm compared to other popular algorithms. We also propose the metricCold Items Precision(CIP) to quantify the ability of a system to recommend cold-start items. CIP can be used in conjunction with relevance ranking metrics like NDCG and MAP to measure the effectiveness of the cold-start recommendation algorithm.</p><h2>Other Information</h2> <p> Published in: Data Mining and Knowledge Discovery<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1007/s10618-020-00708-6" target="_blank">http://dx.doi.org/10.1007/s10618-020-00708-6</a></p>
eu_rights_str_mv openAccess
id Manara2_0a2a9dfb525cf3c5df032d53c42eb29d
identifier_str_mv 10.1007/s10618-020-00708-6
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/21597222
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Simple and effective neural-free soft-cluster embeddings for item cold-start recommendationsShameem A. Puthiya Parambath (14150997)Sanjay Chawla (4254202)Information and computing sciencesApplied computingData management and data scienceDistributed computing and systems softwareRecommender systemsItem recommendationItem cold-start problemSoft-cluster embeddings<p>Recommender systems are widely used in online platforms for easy exploration of personalized content. The best available recommendation algorithms are based on using the observed preference information among collaborating entities. A significant challenge in recommender system continues to be item cold-start recommendation: how to effectively recommend items with no observed or past preference information. Here we propose a two-stage algorithm based on soft clustering to provide an efficient solution to this problem. The crux of our approach lies in representing the items as soft-cluster embeddings in the space spanned by the side-information associated with the items. Though many item embedding approaches have been proposed for item cold-start recommendations in the past—and simple as they might appear—to the best of our knowledge, the approach based on soft-cluster embeddings has not been proposed in the research literature. Our experimental results on four benchmark datasets conclusively demonstrate that the proposed algorithm makes accurate recommendations in item cold-start settings compared to the state-of-the-art algorithms according to commonly used ranking metrics like Normalized Discounted Cumulative Gain (NDCG) and Mean Average Precision (MAP). The performance of our proposed algorithm on the MovieLens 20M dataset clearly demonstrates the scalability aspect of our algorithm compared to other popular algorithms. We also propose the metricCold Items Precision(CIP) to quantify the ability of a system to recommend cold-start items. CIP can be used in conjunction with relevance ranking metrics like NDCG and MAP to measure the effectiveness of the cold-start recommendation algorithm.</p><h2>Other Information</h2> <p> Published in: Data Mining and Knowledge Discovery<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1007/s10618-020-00708-6" target="_blank">http://dx.doi.org/10.1007/s10618-020-00708-6</a></p>2022-11-22T21:13:05ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s10618-020-00708-6https://figshare.com/articles/journal_contribution/Simple_and_effective_neural-free_soft-cluster_embeddings_for_item_cold-start_recommendations/21597222CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/215972222022-11-22T21:13:05Z
spellingShingle Simple and effective neural-free soft-cluster embeddings for item cold-start recommendations
Shameem A. Puthiya Parambath (14150997)
Information and computing sciences
Applied computing
Data management and data science
Distributed computing and systems software
Recommender systems
Item recommendation
Item cold-start problem
Soft-cluster embeddings
status_str publishedVersion
title Simple and effective neural-free soft-cluster embeddings for item cold-start recommendations
title_full Simple and effective neural-free soft-cluster embeddings for item cold-start recommendations
title_fullStr Simple and effective neural-free soft-cluster embeddings for item cold-start recommendations
title_full_unstemmed Simple and effective neural-free soft-cluster embeddings for item cold-start recommendations
title_short Simple and effective neural-free soft-cluster embeddings for item cold-start recommendations
title_sort Simple and effective neural-free soft-cluster embeddings for item cold-start recommendations
topic Information and computing sciences
Applied computing
Data management and data science
Distributed computing and systems software
Recommender systems
Item recommendation
Item cold-start problem
Soft-cluster embeddings