Recommendations from cold starts in big data
Recommendations from cold starts in big data
This paper examines the challenging problem of new user cold starts in subset labelled and extremely sparsely labelled big data. We introduce a new Isle of Wight Supply Chain (IWSC) dataset demonstrating these characteristics. We also introduce a new technique addressing these challenges, the Transitive Semantic Relationships (TSR) model, which infers potential relationships from user and item text content and few labelled examples. We perform both implicit and explicit evaluation of TSR as a recommender system and from new user cold starts we achieve a hit-rate@10 of 77% on a collection of 630 items with only 376 supply-chain consumer labels, and 67% with only 142 supply-chain supplier labels, demonstrating a high level of performance even with extremely few labels in challenging cold-start scenarios. TSR is suitable for any dataset featuring few labels and user and item content, where similarity of content indicates similar relationship forming capability. TSR can be used as a standalone recommender system or to complement existing high-performance recommender models that require more labels or do not support cold starts.
Data mining, Information retrieval, Partially labelled data, Recommender systems, Sparse data
1323-1344
Ralph, David
ea363a70-b796-4912-89c5-e256c5dc1282
Li, Yunjia
0d7cddce-73a2-4554-bc8d-82451a30986e
Wills, Gary
3a594558-6921-4e82-8098-38cd8d4e8aa0
Green, Nicolas G.
d9b47269-c426-41fd-a41d-5f4579faa581
1 June 2020
Ralph, David
ea363a70-b796-4912-89c5-e256c5dc1282
Li, Yunjia
0d7cddce-73a2-4554-bc8d-82451a30986e
Wills, Gary
3a594558-6921-4e82-8098-38cd8d4e8aa0
Green, Nicolas G.
d9b47269-c426-41fd-a41d-5f4579faa581
Ralph, David, Li, Yunjia, Wills, Gary and Green, Nicolas G.
(2020)
Recommendations from cold starts in big data.
Computing, 102 (6), .
(doi:10.1007/s00607-020-00792-y).
Abstract
This paper examines the challenging problem of new user cold starts in subset labelled and extremely sparsely labelled big data. We introduce a new Isle of Wight Supply Chain (IWSC) dataset demonstrating these characteristics. We also introduce a new technique addressing these challenges, the Transitive Semantic Relationships (TSR) model, which infers potential relationships from user and item text content and few labelled examples. We perform both implicit and explicit evaluation of TSR as a recommender system and from new user cold starts we achieve a hit-rate@10 of 77% on a collection of 630 items with only 376 supply-chain consumer labels, and 67% with only 142 supply-chain supplier labels, demonstrating a high level of performance even with extremely few labels in challenging cold-start scenarios. TSR is suitable for any dataset featuring few labels and user and item content, where similarity of content indicates similar relationship forming capability. TSR can be used as a standalone recommender system or to complement existing high-performance recommender models that require more labels or do not support cold starts.
Text
Ralph2020_Article_RecommendationsFromColdStartsI
- Version of Record
More information
Accepted/In Press date: 20 January 2020
e-pub ahead of print date: 29 January 2020
Published date: 1 June 2020
Keywords:
Data mining, Information retrieval, Partially labelled data, Recommender systems, Sparse data
Identifiers
Local EPrints ID: 438699
URI: http://eprints.soton.ac.uk/id/eprint/438699
ISSN: 0010-485X
PURE UUID: db22a368-7e8e-4fca-a24c-a669c6897303
Catalogue record
Date deposited: 23 Mar 2020 17:30
Last modified: 18 Mar 2024 02:59
Export record
Altmetrics
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
