Filters








109,366 Hits in 6.9 sec

Temporal Modeling of User Preferences in Recommender System

Serhii Chalyi, Volodymyr Leshchynskyi
2020 International Conference on Information Control Systems & Technologies  
The adaptation of the model is performed when describing a temporal pattern of the evolution of user requirements by choosing a time interval within which the initial temporal rules are formed.  ...  The model is distinct by the use of temporal rules for building a temporal pattern of periodic changes in user preferences or a description of user requirements' evolution.  ...  The metric 3 dsim allows highlighting a group of users with similar behaviour who have shown interest in the subject i x . Therefore, this metric is focused on building item-based recommendations.  ... 
dblp:conf/icst2/ChalyiL20 fatcat:pde7jtqzw5gwbaksipluhicjei

Dynamic collaborative filtering based on user preference drift and topic evolution

Charinya Wangwatcharakul, Sartra Wongthanavasu
2020 IEEE Access  
We propose a model to capture the user preference dynamics in the rating matrix by using a joint decomposition method to extract user latent transition patterns and combine latent factors together with  ...  Moreover, existing collaborative filtering models mainly rely on solving data sparsity by adding side information to improve performance.  ...  Another interesting extension to our model would be the ability to capture evolving, emerging and fading topic interests of users to improve the prediction performance of the dynamic recommendation system  ... 
doi:10.1109/access.2020.2993289 fatcat:3ugvw7vqybeztjhvjlwzlc75be

Collaborative Filtering Recommendation on Users' Interest Sequences

Weijie Cheng, Guisheng Yin, Yuxin Dong, Hongbin Dong, Wansong Zhang, Wen-Bo Du
2016 PLoS ONE  
With these updated similarities, transition characteristics and dynamic evolution patterns of users' preferences are considered.  ...  Due to the users' unique behavior evolution patterns and personalized interest transitions among items, users' similarity in sequential dimension should be introduced to further distinguish users' preferences  ...  To depict users' dynamic interest evolution patterns, we define the term "interest sequences" and other related concepts in on-line recommendation systems, which are inspired by work in location-based  ... 
doi:10.1371/journal.pone.0155739 pmid:27195787 pmcid:PMC4873175 fatcat:oss7ozg2cbghzfd6unwnqgdlry

Deep Time-Stream Framework for Click-Through Rate Prediction by Tracking Interest Evolution [article]

Shu-Ting Shi, Wenhao Zheng, Jun Tang, Qing-Guo Chen, Yao Hu, Jianke Zhu, Ming Li
2020 arXiv   pre-print
DTS continuously models the evolution of interests using a neural network, and thus is able to tackle the challenge of dynamically representing users' interests based on their historical behaviors.  ...  Experiments on public dataset as well as real industry dataset with billions of samples demonstrate the effectiveness of proposed approaches, which achieve superior performance compared with existing methods  ...  ) DIEN uses GRU with attentional update gate to model the user interest pattern.  ... 
arXiv:2001.03025v1 fatcat:e4sg36fbi5affixyd475bqd32u

Deep Time-Stream Framework for Click-through Rate Prediction by Tracking Interest Evolution

Shu-Ting Shi, Wenhao Zheng, Jun Tang, Qing-Guo Chen, Yao Hu, Jianke Zhu, Ming Li
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
DTS continuously models the evolution of interests using a neural network, and thus is able to tackle the challenge of dynamically representing users' interests based on their historical behaviors.  ...  Experiments on public dataset as well as real industry dataset with billions of samples demonstrate the effectiveness of proposed approaches, which achieve superior performance compared with existing methods  ...  Although improving the performance compared to non-sequential approaches, these RNN based methods still are no enough to represent the user interest evolution without considering time-stream information  ... 
doi:10.1609/aaai.v34i04.6028 fatcat:jl7dtsxea5hp5gamweqbl5kkkm

Incorporating Memory-Based Preferences and Point-of-Interest Stickiness into Recommendations in Location-Based Social Networks

Hang Zhang, Mingxin Gan, Xi Sun
2021 ISPRS International Journal of Geo-Information  
Lastly, we incorporated the influence of both memory-based preferences and POI stickiness into a user-based collaborative filtering framework to improve the performance of POI recommendations.  ...  First, we used the memory-based preference-attenuation mechanism to emphasize personal psychological effects and memory-based preference evolution in human mobility patterns.  ...  Conflicts of Interest: The authors do not declare any conflict of interest.  ... 
doi:10.3390/ijgi10010036 fatcat:igtax6vlpnegret5bmega26gfi

Enhancing Mobile App User Understanding and Marketing with Heterogeneous Crowdsourced Data: A Review

Bin Guo, Yi Ouyang, Tong Guo, Longbing Cao, Zhiwen Yu
2019 IEEE Access  
To enhance mobile app development and marketing, it is important to study the key research challenges such as app user profiling, usage pattern understanding, popularity prediction, requirement and feedback  ...  We first characterize the opportunities of the CrowdApp, and then present the key research challenges and state-of-the-art techniques to deal with these challenges.  ...  group to improve the evolution of each app.  ... 
doi:10.1109/access.2019.2918325 fatcat:de763kc4qbdy5ijo55jxyhzgt4

Sequential Recommendation with Graph Neural Networks [article]

Jianxin Chang, Chen Gao, Yu Zheng, Yiqun Hui, Yanan Niu, Yang Song, Depeng Jin, Yong Li
2021 arXiv   pre-print
In this work, we propose a graph neural network model called SURGE (short for SeqUential Recommendation with Graph neural nEtworks) to address these two issues.  ...  In addition, users' dynamic preferences often change rapidly over time, and hence it is difficult to capture user patterns in their historical sequences.  ...  We study how SURGE improves the recommendation for those users with long behavior records.  ... 
arXiv:2106.14226v1 fatcat:c6inmah6qrh2vlsybo6viftwci

Cloud Synergetic Recommendation Model for Overseas Chinese Education by Modeling Multi-Source User Metaphor Information

Zhehuang Huang
2019 International Journal of Emerging Technologies in Learning (iJET)  
Finally, in order to improve the efficiency of resource acquisition, a recommendation model of Chinese education based on cloud computing is presented.  ...  Firstly, a user vector space with fine granularity representation is constructed by introducing multi-knowledge source emotional metaphor information.  ...  Through the evolution of order parameters, user modes can be identified  Map-Reduce model can improve the efficiency of synergetic user recommendation model Some problems related to synergetic recommendation  ... 
doi:10.3991/ijet.v14i23.11105 fatcat:vnaztdlponefzioi6oh5d4lnxe

Guiding Neuroevolution with Structural Objectives

Kai Olav Ellefsen, Joost Huizinga, Jim Torresen
2019 Evolutionary Computation  
The first structural objective guides evolution to align neural networks with a user-recommended decomposition pattern.  ...  The second structural objective guides evolution towards a population with a high diversity in decomposition patterns.  ...  The experiments were performed on the Abel Cluster, owned by the University of Oslo and the Norwegian metacenter for High Performance Computing (NOTUR), and operated by the Department for Research Computing  ... 
doi:10.1162/evco_a_00250 pmid:30767665 fatcat:2fuud77ztzbjraobojw7ipa7rm

Solving the stability–accuracy–diversity dilemma of recommender systems

Lei Hou, Kecheng Liu, Jianguo Liu, Runtong Zhang
2017 Physica A: Statistical Mechanics and its Applications  
To improve the similarity stability and recommendation stability is crucial for the user experience enhancement and the better understanding of user interests.  ...  systems, while we study the systems' stability with its own natural evolution.  ...  Normally, the system recommends L items with the highest scores to users, and those L items are what the system predicts to have the highest potential to hit the target user's interests.  ... 
doi:10.1016/j.physa.2016.10.083 fatcat:72um25xa2neklbrff7vnfwwfdm

SPDM in Social Media for the Development of Business

2020 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
Data extracted with SPDM is utilized with KNG technique to identify the highly recommended product among clustered users.  ...  Spatial Data Mining(SPDM) are acknowledged as mining of spatial knowledge among attractive pattern from various forms of Spatial Data.  ...  Finally execution, Performance of KNG is compared with KNN which help the business people to take improved decision for the improvement of business. II.  ... 
doi:10.35940/ijitee.e2863.039520 fatcat:jz2wfqahovcudnvpj2cgwfoari

Management of dynamic knowledge

Peter Haase, Johanna Völker, York Sure, John Davies
2005 Journal of Knowledge Management  
of the ontology with respect to the users' requirements.  ...  users and the changes of available data.  ...  With an experiment with the Bibster community we were able to show considerable performance improvements over non-personalized recommendations.  ... 
doi:10.1108/13673270510622483 fatcat:ens6irvcwjaw3aqoti5ywz63du

Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation [article]

Jiayan Guo, Peiyan Zhang, Chaozhuo Li, Xing Xie, Yan Zhang, Sunghun Kim
2022 arXiv   pre-print
Recently, there has been an increasing interest in modeling the user preference evolution to capture the fine-grained user interests.  ...  Session-based recommendation (SBR) aims to predict the user next action based on the ongoing sessions.  ...  Compared with all competitive baselines, the improvements brought by modeling the continuous evolution of user preferences are at most 6.05%, according to the ranking metric on average.  ... 
arXiv:2206.12779v1 fatcat:n3etwoa5rjhirlpazkv7reawrm

Performance of Recommendation Systems in Dynamic Streaming Environments [chapter]

Olfa Nasraoui, Jeff Cerwinske, Carlos Rojas, Fabio Gonzalez
2007 Proceedings of the 2007 SIAM International Conference on Data Mining  
We propose a systematic validation methodology that allows for simulating various controlled user profile evolution scenarios and validating the studied recommendation strategies.  ...  In this paper, we study the behavior of collaborative filtering based recommendations under evolving user profile scenarios.  ...  Hence, in the case of mild everyday evolution of user activity, TECNO-Streams Recommender has better performance, in the sense that, when the environment changes, the quality does not deteriorate as much  ... 
doi:10.1137/1.9781611972771.63 dblp:conf/sdm/NasraouiCRG07 fatcat:poylmnfbvrhdpc75px4evyvrh4
« Previous Showing results 1 — 15 out of 109,366 results