356,703 Hits in 5.7 sec

Using Mutual Influence to Improve Recommendations [chapter]

Aline Bessa, Adriano Veloso, Nivio Ziviani
2013 Lecture Notes in Computer Science  
In this work we show how items in recommender systems mutually influence each other's utility and how it can be explored to improve recommendations.  ...  We propose an algorithm that considers mutual influence to generate recommendations and analyse it over different recommendation datasets.  ...  It is thus possible to take advantage of these mutual influences to improve recommendation systems.  ... 
doi:10.1007/978-3-319-02432-5_6 fatcat:oi7lhxh2vjg35orkpux4hnzwmq

Top-N Recommendation Based on Mutual Trust and Influence

Dewen Seng, Jiaxin Liu, Xuefeng Zhang, Jing Chen, Xujian Fang
2019 International Journal of Computers Communications & Control  
To improve recommendation quality, the existing trust-based recommendation methods often directly use the binary trust relationship of social networks, and rarely consider the difference and potential  ...  To make up for the gap, this paper puts forward a hybrid top-N recommendation algorithm that combines mutual trust and influence.  ...  Recommendation based on mutual trust and influence This section introduces mutual trust and influence to the social recommendation method of the FST, aiming to improve the effectiveness of traditional  ... 
doi:10.15837/ijccc.2019.4.3578 fatcat:bt2vvtyfo5fbpcxj333ficu4dq

Re-ranking With Constraints on Diversified Exposures for Homepage Recommender System [article]

Qi Hao, Tianze Luo, Guangda Huzhang
2021 arXiv   pre-print
Existing re-ranking models are hard to describe the mutual influence between items in both intra-channel and inter-channel.  ...  In the first stage, we develop efficient algorithms for recommending items to proper channels while maintaining diversity.  ...  To model more complex mutual influences, we use the multihead attention. Our encoding module consists of N b blocks of Transformer encoder.  ... 
arXiv:2112.07621v1 fatcat:c2hjfasul5gqrnbuuxqowmtg6a


Evie Octarina, Hartoyo Hartoyo, Irfan Syauqi Beik
2019 Journal of Consumer Sciences  
of sharia mutual fund.  ...  of sharia mutual fund.  ...  Religiosity gives strong influence on attitude which in turn provides strong influence in intention. This can be a recommendation for companies to improve intention to purchase Sharia Mutual Fund.  ... 
doi:10.29244/jcs.4.1.37-47 fatcat:67p4gbeknrhkdc7skaqt6amxpu

Recommendation Algorithms to Increase Equitable Access to Influencers in a Network [article]

Naisha Agarwal
2022 arXiv   pre-print
We propose novel recommendation algorithms to improve fairness in networks. Fairness is measured by how close different nodes are to influencers in the network.  ...  in the network by recommending nodes using an importance sampling algorithm.  ...  It calculates a scale free fairness measure using the influencer set, and improves the fairness in a network via novel node recommendation algorithms.  ... 
arXiv:2109.03217v3 fatcat:tjq6mzgcxjdivfd7jmqgyot5b4

Wine recommendation algorithm based on partitioning and stacking integration strategy for Chinese wine consumers

Weisong Mu, Yumeng Feng, Haojie Shu, Bo Wang, Dong Tian
2022 Italian Journal of Food Science  
The approaches follow the idea of partitioning, decomposing traditional recommendation task into several subtasks according to wine attributes, using neural network, support vector machine (SVM), decision  ...  This study would subserve consumers to choose the wine more easily and conveniently and provide support for wine companies to improve customer satisfaction with consumer services.  ...  Independent variables of wine recommendation subtasks Correlation analysis and significance analysis of variables Mutual information method Mutual information is mainly used to judge the information  ... 
doi:10.15586/ijfs.v34i2.2209 fatcat:ozna55nu7zbizka4z72wfxsd3a

Using Feature Selection Methods to Discover Common Users' Preferences for Online Recommender Systems

Rachael Njeri Ndung'u, Gabriel Ndung'u Kamau, Geoffrey Wambugu Mariga
2021 International Journal of Computer and Information Technology(2279-0764)  
Determination of commonly used attributes that influence preferences used for prediction and subsequent recommendation of unknown or new items to users is a significant objective while developing recommender  ...  Collaborative filtering-based recommender systems uses user opinions and preferences.  ...  We demonstrate how the selected important features have strong influence on response variable, and how they could be used in recommender systems to improve item predictability of any given active user.  ... 
doi:10.24203/ijcit.v10i1.71 fatcat:slpemt7pezhxhh4sfdujt7wfta

The Analysis of Influencing Factors of Performance of Community Time Bank Mutual Assistance Services Based on SEM Model Empirical Data from Nansha District, Guangzhou, China

Daoqin Pan, Yijing Wu
2020 International Journal of Business and Applied Social Science  
Based on the above results, four policy recommendations to promote the sustainable development of community time bank mutual assistance services are also provided.  ...  Therefore, the empirical data from Nansha District, Guangzhou, China, and the Structural Equation Model are used to empirically test the above hypotheses.  ...  The score above convert to a percentage system is 69.63 points. Therefore, the evaluation result of community time bank mutual assistance service performance is considered to be at a medium level.  ... 
doi:10.33642/ijbass.v6n2p1 fatcat:vgydimywb5el5fbyzeg4msughe

Interest-Behaviour Multiplicative Network for Resource-limited Recommendation [article]

Qianliang Wu and Tong Zhang and Zhen Cui and Jian Yang
2020 arXiv   pre-print
In this paper, we aim to mine the cue of user preferences in resource-limited recommendation tasks, for which purpose we specifically build a large used car transaction dataset possessing resource-limitation  ...  To further take the resource limitation into consideration, a resource-limited branch is built to specifically explore the influence of resource variation on user preferences.  ...  ACKNOWLEDGMENTS The authors would like to thank the anonymous reviewers for their constructive comments and the School of Computer Science and Engineering for financial support.  ... 
arXiv:2009.13249v4 fatcat:fyisfwr665bi5k7oips335qykm

Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation

Junliang Yu, Hongzhi Yin, Jundong Li, Qinyong Wang, Nguyen Quoc Viet Hung, Xiangliang Zhang
2021 Proceedings of the Web Conference 2021  
Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems.  ...  Hypergraph provides a natural way to model complex high-order relations, while its potentials for improving social recommendation are under-explored.  ...  Table 3 : 3 General recommendation performance comparison. MHCN 𝑺 2 -MHCN Improv. 𝑺 2 -Improv.  ... 
doi:10.1145/3442381.3449844 fatcat:wmmkxp5rnzc6henb5lnmih7f4m

A Survey-Based Structural Equation Model Analysis on Influencing Factors of Non-Citation

Zewen Hu, Yishan Wu, Jianjun Sun
2018 Current Science  
The survey-based structural equation model was used to analyse mutual relations and correlation degrees between non-citation rate and its various determinants.  ...  approach is not usually used.  ...  factors and their respective influencing degree on NCR using survey-based SEM methods.  ... 
doi:10.18520/cs/v114/i11/2302-2312 fatcat:cyjmwu7mmbhxlltgd2xncqtwwi

Trust Based Stock Recommendation System – A Social Network Analysis Approach

C. Prem Sankar, R. Vidyaraj, K. Satheesh Kumar
2015 Procedia Computer Science  
The analysis of the method using the Indian mutual funds data qualifying CRISIL-1 rating shows that it can effectively be used as a reliable portfolio recommendation system for non-professional investors  ...  We propose a novel system to recommend the leading investment option in stocks utilizing a methodology based on the transactions of trusted mutual funds and their corresponding stock holding portfolio.  ...  This can be further improved by incorporating an expert opinion as the trusted expert advice will lead to better results.  ... 
doi:10.1016/j.procs.2015.02.024 fatcat:7qhje5gfsjhhdlnn6o74w6kdyq

Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation [article]

Junliang Yu, Hongzhi Yin, Jundong Li, Qinyong Wang, Nguyen Quoc Viet Hung, Xiangliang Zhang
2022 arXiv   pre-print
Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems.  ...  Hypergraph provides a natural way to model complex high-order relations, while its potentials for improving social recommendation are under-explored.  ...  We use Adam to optimize all these models. Section 4.4 reports the influence of different parameters (i.e. 𝛽 and the depth) of MHCN, and we use the best parameter settings in Section 4.2, and 4.3.  ... 
arXiv:2101.06448v4 fatcat:dnjuxs7xgjaahod2qfetzj6fsa

Usability of Mutual Aid Mobile App for Emergency care (Preprint)

Ming Ching Lin, Shuo-Chen Chien, Md. Mohaimenul Islam., Chen-An Yeh, Po-Han Chien Chien, Chun-You Chen, Yen-Po Chin
2019 JMIR Formative Research  
Providing immediate cardiopulmonary resuscitation (CPR) to patients might improve survival.  ...  The findings suggest that perceived ease of use and perceived usefulness of the app model affect use willingness. However, perceived usefulness had an intermediary influence on use willingness.  ...  If individuals want to implement an emergency and mutual-aid app model in Taiwan, they need to increase public willingness to use the app, as well as design a convenient user interface to improve perceived  ... 
doi:10.2196/15494 pmid:32191212 pmcid:PMC7118550 fatcat:phr662nrpjctfa7unhpf2ilpye

Contrastive Learning for Cold-Start Recommendation [article]

Yinwei Wei, Xiang Wang, Qi Li, Liqiang Nie, Yan Li, Xuanping Li, Tat-Seng Chua
2021 arXiv   pre-print
Without any historical interaction on cold-start items, CF scheme fails to use collaborative signals to infer user preference on these items.  ...  It allows us to preserve collaborative signals in the content representations for both warm and cold-start items.  ...  It again verifies that the improvements of the cold-start recommendation are mainly obtained by maximizing the mutual information between items' collaborative embeddings and feature representations.  ... 
arXiv:2107.05315v3 fatcat:lwq6nqwpvfbx7curcnkrvwvaka
« Previous Showing results 1 — 15 out of 356,703 results