9 Hits in 3.8 sec

E-Commerce Product Recommendation Agents: Use, Characteristics, and Impact

Xiao, Benbasat
2007 MIS Quarterly  
(2) How do RA use, RA characteristics, and other factors influence users' evaluations of RAs?  ...  The propositions help answer the two research questions: (1) How do RA use, RA characteristics, and other factors influence consumer decision making processes and outcomes?  ...  It offers suggestions about how additional propositions can be developed and how they can be empirically investigated. 4.  ... 
doi:10.2307/25148784 fatcat:4j25zvmnargynp7gjdno3ayeja

CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation [article]

Xidong Feng, Chen Chen, Dong Li, Mengchen Zhao, Jianye Hao, Jun Wang
2021 arXiv   pre-print
CMML is composed of fully feed-forward operations so it is computationally efficient and completely compatible with the mainstream industrial deployment.  ...  With above definitions, the meta recommendation problems can be formulated as the following machine learning problem.  ...  Compared with previous gradient based meta recommendation algorithms, one of the most appealing characteristics for our method is that it is fully composed of feed-forward neural network and successfully  ... 
arXiv:2108.10511v4 fatcat:qgsmmstb6nalze7xdcrevaz5qq

Effects of personal characteristics in control-oriented user interfaces for music recommender systems

Yucheng Jin, Nava Tintarev, Nyi Nyi Htun, Katrien Verbert
2019 User modeling and user-adapted interaction  
However, the effectiveness of interactive interfaces for music recommender systems is likely to be affected by individual differences.  ...  These results allow us to extend the model for personalization in music recommender systems by providing guidelines for interactive visualization design for music recommender systems, with regard to both  ...  This idea can be traced to the work of Schaffer et al. (2015) on meta-recommendation systems, where users are provided with personalized control over the generation of recommendations by altering the  ... 
doi:10.1007/s11257-019-09247-2 fatcat:nxchokl53vhjzf5kw3edzojkti

An Efficient Hybrid Music Recommender System Using an Incrementally Trainable Probabilistic Generative Model

Kazuyoshi Yoshii, Masataka Goto, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno
2008 IEEE Transactions on Audio, Speech, and Language Processing  
We evaluated our system by using audio signals of commercial CDs and their corresponding rating scores obtained from an e-commerce site.  ...  Collaborative filtering, which is used on e-commerce sites, cannot recommend nonbrated pieces and provides a narrow variety of artists.  ...  Although meta recommender systems have been proposed to select a recommender system among conventional ones on the basis of certain quality measures [18] , [19] , the disadvantages of the selected system  ... 
doi:10.1109/tasl.2007.911503 fatcat:lulhfx4gyncqjofhot5rhxor7q

Towards reproducibility in recommender-systems research

Joeran Beel, Corinna Breitinger, Stefan Langer, Andreas Lommatzsch, Bela Gipp
2016 User modeling and user-adapted interaction  
Numerous recommendation approaches are in use today. However, comparing their effectiveness is a challenging task because evaluation results are rarely reproducible.  ...  For instance, the optimal size of an algorithms' user model depended on users' age.  ...  , would ease future research, increase the value of individual research contributions, and support the operators of recommender systems who seek the most effective recommendation approaches for their use  ... 
doi:10.1007/s11257-016-9174-x fatcat:xhcr64duqza73ipqjkgeavgi7a

Market Segmentation in the Film Industry Based on Genre Preference: The Case of Millennials

Dejana Nikolic, Milica Kostic-Stankovic, Veljko Jeremic
2022 Engineering Economics  
One of the industries that has been hit the most by the Covid-19 is the film industry.  ...  To verify the proposed approach, an online survey on consumer habits and attitudes towards different elements of film marketing mix was conducted at the beginning of the Covid-19 lockdown in Serbia.  ...  For example, El Bolock et al. (2020) proposed a film meta recommender algorithm, which starts by getting the genre of films the user prefers before applying machine learning techniques.  ... 
doi:10.5755/ fatcat:taja6vdomfe6bbloxy3vktyvuu

Sparsity-aware neural user behavior modeling in online interaction platforms [article]

Aravind Sankar
2022 arXiv   pre-print
With the rapid proliferation of such online services, learning data-driven user behavior models is indispensable to enable personalized user experiences.  ...  Modern online platforms offer users an opportunity to participate in a variety of content-creation, social networking, and shopping activities.  ...  in task T Q 𝑖 query set for item 𝑖 ∈ I T ,𝑁 in task T 𝐺 𝑈 (• | 𝜃) user encoder in few-shot recommender 𝑹 𝐹 Z 𝑀 set of 𝑀 group embeddings {z 𝑚 ∈ R 𝐷 } 𝑀 𝑚=1 sim 𝑚 similarity metric for meta-recommender  ... 
arXiv:2202.13491v1 fatcat:5lhvre4kpzao5ow7gvxa2qnwhq

Heeding the Call for Change Suggestions for Curricular Action THE MATHEMATICAL ASSOCIATION OF AMERICA MAA Notes and Reports Series

Lynn Steen
In the hope of overcoming these inertias, we offer two clusters of meta-recommendations: Meta-Recommendation I: WORK AT THE GRASS ROOTS The statistics and mathematics professions should do more to support  ...  A fourth section ("Examples") illustrates ways these recommendations can be put into practice, and a final section ("Making It Happen") offers two meta-recommendations about implementation.  ... 

Utilizing Context for Novel Point of Interest Recommendation

Jason M Morawski
One of their uses is for novel point of interest recommendation, recommending locations to a user which they have not visited.  ...  We propose an algorithm for personalized novel point of interest recommendation to overcome these challenges.  ...  Additional weather-based context could be added, to see how temperature, precipitation, and wind affect user behaviour.  ... 
doi:10.7939/r3rv0dd90 fatcat:2gvjnn2evzhu3irvrvxg7au3b4