Multi-level preference regression for cold-start recommendations

Peng, Furong; Lü, Xuan; Ma, Chao; Qian, Yuhua; Lu, Jianfeng; Yang, Jingyu

doi:10.1007/s13042-017-0635-2

Cited by 15 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Recommender systems based on deep neural networks In many studies, supervised learning-based machine learning approaches have been used to address the cold-start problem in recommender systems [28]- [30]. However, this is difficult because recommending an item under cold-start conditions presents similar problems to processing unlabeled data.…”

Section: A Related Work 1) Item-side Cold-start Problems In Recommenmentioning

confidence: 99%

“…In this test, we created groups the number of 600, 500, 400, 300, 200, 100, 50, 40, 30, 20 groups, i.e., comprising 10 to 300 users per group. In each group, we used 10,12,15,20,30,60,120,150,200, and 300 users as the representative number of users. Finally, we compared our method with the CF and NCF approaches, to verify the accuracy of our results.…”

Section: Experiments and Analysis A Experiments Designmentioning

confidence: 99%

See 1 more Smart Citation

Alleviating Item-Side Cold-Start Problems in Recommender Systems Using Weak Supervision

et al. 2020

View full text Add to dashboard Cite

Recently, recommender systems have been used in various fields. However, they are still plagued by many issues, including cold-start and sparsity problems. The cold-start problem occurs when users are unable to make recommendations to other users owing to a complete lack of information about certain items. This problem can exist both at the user side and the item side. User-side cold-start problems occur when new users access the systems; item-side cold-start problems occur when new items are added to databases. In this study, we addressed the item-side cold-start problem using the concept of weak supervision. First, a new process for identifying feature based representative reviewers in a rater group was designed. Then, we developed a method to predict the expected preferences for new items by combining content-based filtering and the preferences of representative users. Through extensive experiments, we first confirmed that in comparison to existing methods, the proposed approach provided enhanced accuracy, which was evaluated by determining a mean absolute error for the average ratings. Then, we compared the proposed scheme with the collaborative filtering (CF) and neural CF approaches (NCF). The estimation by the proposed approach was 21% and 38% more accurate than CF and NCF in terms of mean absolute error (MAE), respectively. In future, the proposed framework can be applied in various recommender systems as a core function.

show abstract

Section: A Related Work 1) Item-side Cold-start Problems In Recommenmentioning

confidence: 99%

Section: Experiments and Analysis A Experiments Designmentioning

confidence: 99%

Alleviating Item-Side Cold-Start Problems in Recommender Systems Using Weak Supervision

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Based on the above two modules, various solutions are being investigated. Matrix factorization is one of the most commonly used methods to solve the cold-start user problem [10][11][12]. Social network analysis (SNA) is another common method.…”

Section: Related Workmentioning

confidence: 99%

User Group-based Method for Cold-Start Recommendation

He¹,

Yuan²,

Xiang³

et al. 2018

IJPE

View full text Add to dashboard Cite

Recommendation algorithms seek to predict user ratings or preferences. Due to limited information, it is difficult to make these predictions for new users. Therefore, a dynamic cold-start recommendation algorithm would be highly helpful in such quick-changing social networks. In this paper, a novel user group-based collaborative method, called UCFRA (User group-based Cold-start Friend Recommendation Algorithm) is proposed. UCFRA integrates a graphical model and statistical population characteristics into a user group model and then combines this extended user group model with cold-start information to generate a new recommendation algorithm. Moreover, a content popularity model based on user groups and a user rating matrix is designed. In order to improve recommend precision, a user group Top-N recommendation model based on k-nearest neighbors is provided. A series of experiments involving collection of a huge data set was developed to evaluate the effectiveness of UCFRA. The experimental results showed that UCFRA is a valid algorithm.

show abstract

“…Wongchokprasi i et al studied the possibility to use user models built by one system to another to address the cold start problem [56]. Peng et al present a method to be er weight the impact of user's a ributes, preferences and item's popularity in multi-level regression model [46]. Guo et al focused on both user modeling and trust modeling [25].…”

Section: User Cold-start Recommendationmentioning

confidence: 99%

A Multi-Armed Bandit Model Selection for Cold-Start User Recommendation

Felício

Paixão

Barcelos

et al. 2017

Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization

View full text Add to dashboard Cite

How can we e ectively recommend items to a user about whom we have no information? is is the problem we focus on in this paper, known as the cold-start problem. In most existing works, the cold-start problem is handled through the use of many kinds of information available about the user. However, what happens if we do not have any information? Recommender systems usually keep a substantial amount of prediction models that are available for analysis. Moreover, recommendations to new users yield uncertain returns. Assuming that a number of alternative prediction models is available to select items to recommend to a cold user, this paper introduces a multi-armed bandit based model selection, named PdMS. In comparison with three baselines, PdMS improves the performance as measured by the nDCG. ese improvements are demonstrated on real, public datasets.

show abstract

Multi-level preference regression for cold-start recommendations

Cited by 15 publications

References 34 publications

Alleviating Item-Side Cold-Start Problems in Recommender Systems Using Weak Supervision

Alleviating Item-Side Cold-Start Problems in Recommender Systems Using Weak Supervision

User Group-based Method for Cold-Start Recommendation

A Multi-Armed Bandit Model Selection for Cold-Start User Recommendation

Contact Info

Product

Resources

About