Attributes coupling based matrix factorization for item recommendation

Yu, Yonghong; Wang, Can; Wang, Hao; Gao, Yang

doi:10.1007/s10489-016-0841-8

Cited by 52 publications

(33 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Item features, which are generated by domain experts to represent item characteristics [17], have been utilized with different techniques proposed for combining them with MF to improve the recommendation performance. For instance, Nguyen and Zhu et al [16] propose the incorporation of content information into MF, whereby the similarity between items, utilizing the 'Simple Matching Similarity' measurement, is first computed, followed by extending the MF framework with the computed similarities.…”

Section: B Matrix Factorization Enriched With Item Featuresmentioning

confidence: 99%

“…Compared to user sideinformation, item side-information is more readily available and easier to collect in real-world applications. Item sideinformation, such as item features that are generated by domain experts to represent item characteristics, has been popular as a source of information to be tapped into and incorporated into MF schemes [16], [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

FeatureMF: An Item Feature Enriched Matrix Factorization Model for Item Recommendation

et al. 2021

View full text Add to dashboard Cite

Matrix Factorization (MF) is one of the most successful Collaborative Filtering (CF) techniques used in recommender systems due to its effectiveness and ability to deal with very large useritem rating matrix. However, when the rating matrix sparseness increases its performance deteriorates. Expanding MF to include side-information of users and items has been shown by many both to improve general recommendation performance and to help alleviate the sparsity and cold-start issues in CF. In regard to item feature side-information, most schemes incorporate this information through a two stage process: intermediate results (e.g., on item similarity) are first computed based on item attributes; these are then combined with MF. In this paper, focussing on item side-information, we propose a model that directly incorporates item features with the MF framework in a single step process. The model, which we name FeatureMF, does this by projecting every available attribute datum in each of the item features into the same latent factor space with users and items, thereby in effect enriching item representation in the MF model. Results are presented of comparative performance experiments of the model against three state-ofthe-art item information enriched models, as well as against four reference benchmark models, using two public real-world datasets, Douban and Yelp, with four training:test ratio scenarios each. It is shown to yield the best recommendation performance over all these models across all contexts including data sparsity situations, in particular, achieving over 0.9% to over 6.5% MAE recommendation performance improvement over the next best model, HERec. The model is also found to alleviate cold start and to scale well, almost linearly, in regard to computational time, as a function of dataset size.

show abstract

Section: B Matrix Factorization Enriched With Item Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

FeatureMF: An Item Feature Enriched Matrix Factorization Model for Item Recommendation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Social information the "credibility" of users [7], social relationships of users discovered by social networks [8] Social behaviors of users Users' browsing behaviors [9], users' point of interest [10] Opinions of users Comments given by users [11,12] Information of items Items' reputations, semantic contents [6] and items' attributes [5,13] Tag information Tags annotated by users and tags provided by systems [14] Beside the basic descriptions of users and items, tag information, which has been incorporated into hybrid CBF/CF algorithms by being used to calculate user-based and item-based similarity measures [14], is a kind of useful semantic information for recommendation systems.…”

Section: Categories Detailed Descriptionmentioning

confidence: 99%

An Extended-Tag-Induced Matrix Factorization Technique for Recommender Systems

et al. 2018

View full text Add to dashboard Cite

Social tag information has been used by recommender systems to handle the problem of data sparsity. Recently, the relationships between users/items and tags are considered by most tag-induced recommendation methods. However, sparse tag information is challenging to most existing methods. In this paper, we propose an Extended-Tag-Induced Matrix Factorization technique for recommender systems, which exploits correlations among tags derived by co-occurrence of tags to improve the performance of recommender systems, even in the case of sparse tag information. The proposed method integrates coupled similarity between tags, which is calculated by the co-occurrences of tags in the same items, to extend each item's tags. Finally, item similarity based on extended tags is utilized as an item relationship regularization term to constrain the process of matrix factorization. MovieLens dataset and Book-Crossing dataset are adopted to evaluate the performance of the proposed algorithm. The results of experiments show that the proposed method can alleviate the impact of tag sparsity and improve the performance of recommender systems.

show abstract

“…Hybrid method combines the advantages of the both CBR and CF methods and overcomes the limitations of these methods. However, there arises complexity in designing a hybrid system for the app recommendations and also it is completely different from developing traditional recommender system for item recommendations like movie, books, music and so on [13], [14]. Generally changes in the version updates of every App is demonstrated by its version numbers and descriptions.…”

Section: Introductionmentioning

confidence: 99%

PEVRM: Probabilistic Evolution Based Version Recommendation Model for Mobile Applications

Maheswari

Geetha

Kumar³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Traditional recommendation approaches for the mobile apps basically depend on the app related features. Now a days many users are in quench of app recommendation based on the version description. In the proposed system the hybrid app recommending framework is introduced which is considering the version of the mobile apps. This novel framework named "Probabilistic Evolution based Version Recommendation Model (PEVRM)" integrates the principles of Probabilistic Matrix Factorization (PMF) with Version Evolution Progress Model (VEPM). With the help this novel recommendation algorithm, the mobile users easily identify the specific apps for particular task based on its version progression. At same time, this framework helps in resolving cold start problems of new users. Evaluations of this framework utilize a benchmark dataset, i.e., Apple's iTunes App Store3, for revealing its promising performance.

show abstract

Attributes coupling based matrix factorization for item recommendation

Cited by 52 publications

References 32 publications

FeatureMF: An Item Feature Enriched Matrix Factorization Model for Item Recommendation

FeatureMF: An Item Feature Enriched Matrix Factorization Model for Item Recommendation

An Extended-Tag-Induced Matrix Factorization Technique for Recommender Systems

PEVRM: Probabilistic Evolution Based Version Recommendation Model for Mobile Applications

Contact Info

Product

Resources

About