Filters








3,816 Hits in 5.5 sec

Fast Matrix Factorization for Online Recommendation with Implicit Feedback

Xiangnan He, Hanwang Zhang, Min-Yen Kan, Tat-Seng Chua
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
My research interests span information retrieval, machine learning, data mining and their applications in personalization, recommender systems and computational advertising.  ...  Currently, I am working on 1) developing recommender algorithms for social groups, 2) designing deep learning methods for predictive analytics. Educations  ...  Immanuel Da Cao, Xiangnan He, Liqiang Nie, Xiaochi Wei, Xia Hu, Shunxiang Wu and Tat-Seng Chua (2017). Cross-Platform App Recommendation by Jointly Modeling Ratings and Texts.  ... 
doi:10.1145/2911451.2911489 dblp:conf/sigir/HeZKC16 fatcat:gv2ufvp4enhgbl2gbnphsgj43y

Eliciting Auxiliary Information for Cold Start User Recommendation: A Survey

Nor Aniza Abdullah, Rasheed Abubakar Rasheed, Mohd Hairul Nizam Md. Nasir, Md Mujibur Rahman
2021 Applied Sciences  
learning prediction models.  ...  information; (2) the obtained implicit auxiliary information is usually ranked and sieved in order to select the top rated and reliable auxiliary information for the recommendation.  ...  The study developed a hybrid factorization matrix factorization model that jointly exploit user preferences and item metadata for cross-domain recommendation.  ... 
doi:10.3390/app11209608 fatcat:foxbu3gt4fdxhdxuhijtufkyiu

Learning Continuous User Representations through Hybrid Filtering with doc2vec [article]

Simon Stiebellehner, Jun Wang, Shuai Yuan
2017 arXiv   pre-print
Second, we introduce context awareness to that model by incorporating additional user and app-related metadata in model training (context2vec).  ...  First, we model mobile app users through their app usage histories and app descriptions (user2vec).  ...  Matching of supply and demand is facilitated by technology platforms that are referred to as "supply-side" and "demand-side" platforms.  ... 
arXiv:1801.00215v1 fatcat:avcszeivnjbjxkem6nfe4ctjci

Improving B2B2C Strategies through Digital Technologies for Cross-Border Commerce between Thailand and China

Bibi She, Siva Shankar Ramasamy, Piang-or Loahavilai, Nopasit Chakpitak
2020 Journal of Southwest Jiaotong University  
The applet will serve Thai merchants by helping them overcome language barrieres, cross-border transfers, and post-sales services.  ...  Today's world is moving toward a New Normal Life style, particularly in regard to e-commerce methods and updated platforms.  ...  ACKNOWLEDGMENT The authors acknowledge the mentors of the International College of Digital Innovation-CMU for their guidance and Support.  ... 
doi:10.35741/issn.0258-2724.55.6.23 fatcat:t6whhkc3yfazteovldns2lmcj4

Use of Machine Learning to Mine User-Generated Content From Mobile Health Apps for Weight Loss to Assess Factors Correlated With User Satisfaction

Tong Wang, Xu Zheng, Jun Liang, Kai An, Yunfan He, Mingfu Nuo, Wei Wang, Jianbo Lei
2022 JAMA Network Open  
rating in the app stores, were analyzed by the Wald test.  ...  Differences of the coefficients in models of positive rating deviation (PD) and negative rating deviation (ND), defined as the difference between the users' rating of the app and the app's comprehensive  ...  The optimal number of topics is generally determined jointly by the perplexity and the actual clustering performance of the LDA model.  ... 
doi:10.1001/jamanetworkopen.2022.15014 pmid:35639374 fatcat:jcsqopt3j5ddfpimffvfddo45y

Adoption of Mobile Payment Platforms: Managing Reach and Range

Kalina S Staykova, Jan Damsgaard
2016 Journal of Theoretical and Applied Electronic Commerce Research  
In this paper, we investigate successful platform adoption strategies by using the Reach and Range Framework for Multi-Sided Platforms as a strategic tool to which mobile payment providers can adhere in  ...  Our study showcases that the success of mobile payment platforms lies with the ability of the platform to balance the reach (number of participants) and the range (features and functionalities) of the  ...  By enabling cross-side functionality, a platform could unlock new uses for its app and expand its overall reach.  ... 
doi:10.4067/s0718-18762016000300006 fatcat:fav5usaojzcrfe4fnznxfvjmum

The Personal Health Library (PHL): Enabling an mHealth Recommender System for Self-Management of Diabetes among Underserved Population with Multiple Chronic Conditions (Preprint)

Nariman Ammar, James E Bailey, Robert L Davis, Arash Shaban-Nejad
2020 JMIR Formative Research  
By exposing the PHL functionality as an open service, we foster the development of third-party applications or services and provide motivational technological support in several projects crossing different  ...  We leverage the Social Linked Data (Solid) platform to design a fully decentralized and privacy-aware platform that supports interoperability and care integration.  ...  The goal is to reveal issues related to the (1) usability, (2) clinical content, and (3) educational content of both the (a) PHL platform and (b) recommendations produced by the app.  ... 
doi:10.2196/24738 pmid:33724197 fatcat:zdkjkq6ldng4hekdgvvqyteguu

EENMF: An End-to-End Neural Matching Framework for E-Commerce Sponsored Search [article]

Wenjin Wu, Guojun Liu, Hui Ye, Chenshuang Zhang, Tianshu Wu, Daorui Xiao, Wei Lin, Xiaoyu Zhu
2018 arXiv   pre-print
Besides, the proposed model tries to optimize the pointwise cross-entropy loss which is consistent with the objective of predict models in the ranking stage.  ...  We propose an end-to-end neural matching framework (EENMF) to model two tasks---vector-based ad retrieval and neural networks based ad pre-ranking.  ...  [8] proposed an App recommender system for Google Play with a wide & deep model. Covington et al.  ... 
arXiv:1812.01190v4 fatcat:qlg2miqiofc4nncucgulrknuj4

Developing Multi-Task Recommendations with Long-Term Rewards via Policy Distilled Reinforcement Learning [article]

Xi Liu, Li Li, Ping-Chun Hsieh, Muhe Xie, Yong Ge, Rui Chen
2020 arXiv   pre-print
The resulting model is expected to attain better performance and lower response latency for real-time recommendation services.  ...  the size of a learning model.  ...  Taking app items as an example, the type of information available for an app ranges from unstructured data such as image and text to structured data such as app profiles, and aggregated user feedback to  ... 
arXiv:2001.09595v1 fatcat:pecutlfpyzc75j4utec7z2cq3y

User Response Prediction in Online Advertising [article]

Zhabiz Gharibshah, Xingquan Zhu
2021 arXiv   pre-print
Online advertising, as the vast market, has gained significant attention in various platforms ranging from search engines, third-party websites, social media, and mobile apps.  ...  In this survey, we provide a comprehensive review of user response prediction in online advertising and related recommender applications.  ...  This is partially related to cross-domain recommendation approaches that a pre-trained recommendation model is applied to different downstream tasks [171] .  ... 
arXiv:2101.02342v2 fatcat:clgefamcd5fmbeg5ephizy3zqu

Telepath: Understanding Users from a Human Vision Perspective in Large-Scale Recommender Systems

Yu Wang, Jixing Xu, Aohan Wu, Mantian Li, Yang He, Jinghe Hu, Weipeng Yan
2018 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
For one of the major item recommendation blocks on the JD app, click-through rate (CTR), gross merchandise value (GMV) and orders have been increased 1.59%, 8.16% and 8.71% respectively by Telepath.  ...  For several major ad publishers of JD demand-side platform, CTR, GMV and return on investment have been increased 6.58%, 61.72% and 65.57% respectively by the first launch of Telepath, and further increased  ...  For a major item recommendation block in JD app, the CTR (click-through rate), GMV and orders have been increased 1.59%, 8.16% and 8.71% respectively.  ... 
doi:10.1609/aaai.v32i1.11243 fatcat:hd6v7ouxtfhgjmuikvwdw7ct4q

Telepath: Understanding Users from a Human Vision Perspective in Large-Scale Recommender Systems [article]

Yu Wang, Jixing Xu, Aohan Wu, Mantian Li, Yang He, Jinghe Hu, Weipeng P. Yan
2017 arXiv   pre-print
For one of the major item recommendation blocks on the JD app, click-through rate (CTR), gross merchandise value (GMV) and orders have increased 1.59%, 8.16% and 8.71% respectively.  ...  In practice, the Telepath model has been launched to JD's recommender system and advertising system.  ...  For a major item recommendation block in JD app, the CTR (click-through rate), GMV and orders increased 1.59%, 8.16% and 8.71% respectively.  ... 
arXiv:1709.00300v2 fatcat:j2enntxjhje5jlpqtqjr3d5cdi

A Survey on Cross-domain Recommendation: Taxonomies, Methods, and Future Directions [article]

Tianzi Zang, Yanmin Zhu, Haobing Liu, Ruohan Zhang, Jiadi Yu
2022 arXiv   pre-print
Traditional recommendation systems are faced with two long-standing obstacles, namely, data sparsity and cold-start problems, which promote the emergence and development of Cross-Domain Recommendation  ...  In this survey paper, we first proposed a two-level taxonomy of cross-domain recommendation which classifies different recommendation scenarios and recommendation tasks.  ...  users and apps.  ... 
arXiv:2108.03357v2 fatcat:ywwh44x3pfbnbesy5ojogg4hyy

Version-sensitive mobile App recommendation

Da Cao, Liqiang Nie, Xiangnan He, Xiaochi Wei, Jialie Shen, Shunxiang Wu, Tat-Seng Chua
2017 Information Sciences  
It is able to recommend appropriate Apps to right users by jointly exploring the version progression and dual-heterogeneous data.  ...  Users, however, are frequently overwhelmed by the vast number of released Apps and frequently updated versions.  ...  Acknowledgments The authors are highly grateful to the anonymous referees for their careful reading and insightful comments.  ... 
doi:10.1016/j.ins.2016.11.025 fatcat:jlwoqumu3ndjdmf52qu2k2dnhm

Science Driven Innovations Powering Mobile Product: Cloud AI vs. Device AI Solutions on Smart Device [article]

Deguang Kong
2017 arXiv   pre-print
and deep learning, user modeling and marketing techniques to bring in significant user growth and user engagement and satisfactions (and happiness) on mobile devices.  ...  On one hand, rich user profiling and behavior data (including per-app level, app-interaction level and system-interaction level) from heterogeneous information sources make it possible to provide much  ...  Any opinions, findings or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of any company.  ... 
arXiv:1711.07580v1 fatcat:t5xpvqvsa5d3piqbl24itrb2bq
« Previous Showing results 1 — 15 out of 3,816 results