24 Hits in 6.0 sec

Supercharging Recommender Systems using Taxonomies for Learning User Purchase Behavior [article]

Bhargav Kanagal, Amr Ahmed, Sandeep Pandey, Vanja Josifovski, Jeff Yuan, Lluis Garcia-Pueyo
2012 arXiv   pre-print
Recommender systems based on latent factor models have been effectively used for understanding user interests and predicting future actions.  ...  We empirically evaluate the TF model for the task of predicting user purchases using a real-world shopping dataset spanning more than a million users and products.  ...  These systems use the past behavior of users to recommend new items that are likely to be of interest to them.  ... 
arXiv:1207.0136v1 fatcat:emtgfgeirneelcdecsj5b4xivq

Supercharging recommender systems using taxonomies for learning user purchase behavior

Bhargav Kanagal, Amr Ahmed, Sandeep Pandey, Vanja Josifovski, Jeff Yuan, Lluis Garcia-Pueyo
2012 Proceedings of the VLDB Endowment  
Recommender systems based on latent factor models have been effectively used for understanding user interests and predicting future actions.  ...  We empirically evaluate the TF model for the task of predicting user purchases using a real-world shopping dataset spanning more than a million users and products.  ...  These systems use the past behavior of users to recommend new items to them that are likely to be of interest.  ... 
doi:10.14778/2336664.2336669 fatcat:2sg2w6vfjrcizprefddiidacva

Research Commentary on Recommendations with Side Information: A Survey and Research Directions [article]

Zhu Sun, Qing Guo, Jie Yang, Hui Fang, Guibing Guo, Jie Zhang, Robin Burke
2019 arXiv   pre-print
One involves the different methodologies of recommendation: the memory-based methods, latent factor, representation learning, and deep learning models.  ...  Traditional recommender systems, however, suffer from data sparsity and cold start problems.  ...  ACKNOWLEDGEMENTS This work was partly conducted within the Delta-NTU Corporate Lab for Cyber-Physical Systems with funding support from Delta Electronics Inc. and the National Research Foundation (NRF)  ... 
arXiv:1909.12807v2 fatcat:2nj4crzcd5attidhd3kneszmki

Seeing like a market

Marion Fourcade, Kieran Healy
2016 Socio-Economic Review  
For organizations they create new opportunities to structure and price o erings to their consumers, and for individuals they create classi cation situations that identify shared life-chances in various  ...  We argue, rst, that modern organizations follow an institutional data imperative to collect as much data as possible; second, that as a result of the analysis and use of this data individuals accrue übercapital  ...  Payment systems and repayment practices now differentiate us from one another, and for the bene t of the market.  ... 
doi:10.1093/ser/mww033 fatcat:2vctxhhombftjitihp7mh4uff4

Beyond bowling together

Paul Resnick, Tora Bikson, Elizabeth Mynatt, Robert Puttnam, Lee Sproull, Barry Wellman
2000 Proceedings of the 2000 ACM conference on Computer supported cooperative work - CSCW '00  
A new theoretical construct, SocioTechnical Capital, provides a framework for generating and evaluating technology-mediated social relations.  ...  HCI researchers and practitioners need to find new ways for people to interact that will generate even more social capital than bowling together does.  ...  Recommender systems (Resnick and Varian 1997) can supercharge this process, allowing recommendation sharing among people who may not know each other or be explicitly aware of each other's interests.  ... 
doi:10.1145/358916.362079 dblp:conf/cscw/ResnickBMPSW00 fatcat:qbzhytcpjffojalxonz5tnakgm

The State of AI Ethics Report (Volume 5) [article]

Abhishek Gupta
2021 arXiv   pre-print
working on AI ethics issues, the report also features two spotlights sharing the work of scholars operating in Singapore and Mexico helping to shape policy measures as they relate to the responsible use  ...  Further, since recommendations are extremely effective at altering user behavior, dating apps are influencing the intimate behaviors of their users.  ...  After all, recommendations can and do change the behavior and preferences of users.  ... 
arXiv:2108.03929v1 fatcat:rhc6bdeesbaqjlnlu4x5iyesay

The Third AI Summer: AAAI Robert S. Engelmore Memorial Lecture

Henry Kautz
2022 The AI Magazine  
Software startups sold expert system "shells," that is, reasoning engines with user interfaces intended to make it possible for nonprogrammers to enter rules.  ...  Since then, of course, user modeling from From Liao, Fox, and Kautz (2007) mobile phone data has exploded, fusing data from GPS, social media posts, purchases, and in certain nations, the contents of  ...  His interdisciplinary research includes practical algorithms for solving worst-case intractable problems in logical and probabilistic reasoning; models for inferring human behavior from sensor data; pervasive  ... 
doi:10.1609/aimag.v43i1.19122 fatcat:vrymeyxjdbhr3etnvdegqxjypa

News briefs

1993 Journal of Research of the National Institute of Standards and Technology  
ADEC has devised likely oil-spill scenarios to use in the program and has provided two types of Alaskan crude oil for testing.  ...  This 3 year project will help ADEC develop guidelines officials at an oil-spill site can use to evaluate the effects of burning.  ...  and recommend policies on the use of networking standards by the federal government.  ... 
doi:10.6028/jres.098.050 fatcat:h45ke7batnd4tmi4gkruye4stq

Evolution of the big deals use in the public universities of the Castile and Leon region, Spain

Andrés Fernández-Ramos, Blanca Rodríguez-Bravo, María-Luisa Alvite-Díez, Lourdes Santos-De-Paz, María-Antonia Morán-Suárez, Josefa Gallego-Lorenzo, Isabel Olea
2020 El Profesional de la Informacion  
LAUNCHcast is also learning from other listeners and using their opinions to guide its recommendations. Because this is an online service with millions of users, Yahoo!  ...  We are now spoiled with useful recommendations (lessons learned by those who came before us) that introduce us to things we never would have thought of or found on our own.  ...  From collaborative filtering to user ratings, smart aggregators are using rec- PERCENTAGE OF TOTAL SALES Title Rank Wal-Mart* Rhapsody Blockbuster* Netflix 1-100 65% 47% 68% 38% 101 and up 36% 53%  ... 
doi:10.3145/epi.2019.nov.19 fatcat:7hb7lt2ryrdt5o33xjjcoduuli

Learning Intents behind Interactions with Knowledge Graph for Recommendation [article]

Xiang Wang, Tinglin Huang, Dingxian Wang, Yancheng Yuan, Zhenguang Liu, Xiangnan He, Tat-Seng Chua
2021 pre-print
This scheme allows us to distill useful information about user intents and encode them into the representations of users and items.  ...  Knowledge graph (KG) plays an increasingly important role in recommender systems. A recent technical trend is to develop end-to-end models founded on graph neural networks (GNNs).  ...  Here we focus on the implicit feedback [26] in recommendation, where the signal that a user provides about her preference is implicit (e.g., view, click, purchase).  ... 
doi:10.1145/3442381.3450133 arXiv:2102.07057v1 fatcat:xsldoswspnddrdpm2qs63m6ave

On TESOL '82: Pacific Perspectives on Language Learning and Teaching

David P. Harris, Mark A. Clarke, Jean Handscombe
1984 The Modern Language Journal  
The volume is divided into four sections: (1) Policy and Planning, (2) Challenging Assumptions, (3) Conditions for Learning, and (4) In--or out of--the Classroom.  ...  The final section contains 10 papers dealing with the organization of the learning experience at the level of program/curriculum planning, classroom management, and materials development. (Author/AMH)  ...  This recommendation was implemented in 1924, and was called the English Standard system.  ... 
doi:10.2307/327744 fatcat:p7vwkrxo7zhpjl7iid2afb3yea

Seeing like a market

Marion Fourcade, Kieran Healy
We present a new theoretical framework for understanding them.  ...  For individuals, they create classification situations that identify shared life-chances in product and service markets.  ...  A machine or 'deep' learning system may decide for itself which general rules and variables to use for prediction, in a manner that is opaque to most of its users (Burrell, 2016) .  ... 
doi:10.17605/ fatcat:dyr6ruykxrgotepreht67wecsq

Dingliche Kreditsicherheiten in der Insolvenz in Mittel-und Osteuropa herausgegeben von

Martin Winner, Romana Cierpial-Magnor, Wolfie Christl, Sarah Spiekermann
It also remains unknown how user attributes or behaviors were identified, which personal data was used, whether additional data was purchased and which algorithms were used.  ...  Through technical measurement they discovered differences in the products shown to users based on the history of clicked or purchased products, and their operating system or browserfor example, when using  ... 

Authentic learning and marketing education in a marketing simulation game

Jeffrey Skolnick
"Authentic learning involves [the] alignment of student learning experiences with the world for which they are being prepared" (McKenzie et al. 2002, p.427).  ...  Despite the considerable literature on the use of simulation games in marketing education there is little research on students' experiences, including student perceptions of simulation games and learning  ...  I also need to thank them for exiling me to Phillip Island for many quiet but productive weekends. This thesis was edited in terms of language and grammar.  ... 
doi:10.4225/03/58b60ab406ad8 fatcat:zzke243dczbjzpno5s7g6vjzx4

Essays on Multi-product Pricing

Marcel Goic
Managers often make price decisions for several products simultaneously. By doing so, decision makers can control for substitution effects or take advantage of potential synergies between products.  ...  2 The model is well defined for ( 1  ...  We use those conditions to estimate an empirical model of purchase behavior that enables us to identify the likelihood of each consumer buying from the competitor or simply changing his consumption patterns  ... 
doi:10.1184/r1/6716441 fatcat:lydhhdetcjgb7e6fltoeiz6fr4
« Previous Showing results 1 — 15 out of 24 results