Optimized Ranking-Based Techniques for Improving Aggregate Recommendation Diversity

Saravana Kumar Naveen Kumar

ISBN 10: 3656563241 ISBN 13: 9783656563242

Edit� par GRIN Verlag, 2013

Neuf(s) Couverture souple

Vendeur Books Puddle, New York, NY, Etats-Unis �valuation du vendeur 4 sur 5 �toiles

Vendeur AbeBooks depuis 22 novembre 2018

Cet article sp�cifique n'est plus disponible.

Afficher tous les articles du vendeur Cr�er une demande de livres portant sur des articles similaires

Afficher tous les exemplaires de ce livre

A propos de cet article

pp. 20. N� de r�f. du vendeur 26127602453

Signaler cet article

Synopsis :

Master's Thesis from the year 2013 in the subject Computer Science - Miscellaneous, grade: 1, course: ME computer science, language: English, abstract: This paper investigates how demand-side factors contribute to the Internet's "Long Tail" phenomenon. It first models how a reduction in search costs will affect the concentration in product sales. Then, by analyzing data collected from a multi-channel retailing company, it provides empirical evidence that the Internet channel exhibits a significantly less concentrated sales distribution, when compared with traditional channels. The difference in the sales distribution is highly significant, even after controlling for consumer differences. Furthermore, the effect is particularly strong for individuals with more prior experience using the Internet channel. We find evidence that Internet purchases made by consumers with prior Internet experience are more skewed toward obscure products, compared with consumers who have no such experience. We observe the opposite outcome when comparing purchases by the same consumers through the catalog channel. If the relationships we uncover persist, the underlying trends in technology and search costs portend an ongoing shift in the distribution of product sales. Singular Value Decomposition (SVD), together with the Expectation-Maximization (EM) procedure, can be used to find a low-dimension model that maximizes the log likelihood of observed ratings in recommendation systems. However, the computational cost of this approach is a major concern, since each iteration of the EM algorithm requires a new SVD computation. We present a novel algorithm that incorporates SVD approximation into the EM procedure to reduce the overall computational cost while maintaining accurate predictions. Furthermore, we propose a new framework for collaborating filtering in distributed recommendation systems that allows users to maintain their own rating profiles for privacy. We conduct offline and online t

Les informations fournies dans la section � A propos du livre � peuvent faire r�f�rence � une autre �dition de ce titre.

D�tails bibliographiques

Titre : Optimized Ranking-Based Techniques for ...
�diteur : GRIN Verlag
Date d'�dition : 2013
Reliure : Couverture souple
Etat : New

Meilleurs r�sultats de recherche sur AbeBooks

Image fournie par le vendeur

Optimized Ranking-Based Techniques for Improving Aggregate Recommendation Diversity

Naveen Kumar

Edit� par GRIN Verlag, 2013

ISBN 10 : 3656563241 ISBN 13 : 9783656563242

Neuf Taschenbuch

Vendeur : AHA-BUCH GmbH, Einbeck, Allemagne

�valuation du vendeur 5 sur 5 �toiles

Taschenbuch. Etat : Neu. Druck auf Anfrage Neuware - Printed after ordering - Master's Thesis from the year 2013 in the subject Computer Science - Miscellaneous, grade: 1, , course: ME computer science, language: English, abstract: This paper investigates how demand-side factors contribute to the Internet's 'Long Tail' phenomenon. It first models how a reduction in search costs will affect the concentration in product sales. Then, by analyzing data collected from a multi-channel retailing company, it provides empirical evidence that the Internet channel exhibits a significantly less concentrated sales distribution, when compared with traditional channels. The difference in the sales distribution is highly significant, even after controlling for consumer differences. Furthermore, the effect is particularly strong for individuals with more prior experience using the Internet channel. We find evidence that Internet purchases made by consumers with prior Internet experience are more skewed toward obscure products, compared with consumers who have no such experience. We observe the opposite outcome when comparing purchases by the same consumers through the catalog channel. If the relationships we uncover persist, the underlying trends in technology and search costs portend an ongoing shift in the distribution of product sales. Singular Value Decomposition (SVD), together with the Expectation-Maximization (EM) procedure, can be used to find a low-dimension model that maximizes the log likelihood of observed ratings in recommendation systems. However, the computational cost of this approach is a major concern, since each iteration of the EM algorithm requires a new SVD computation. We present a novel algorithm that incorporates SVD approximation into the EM procedure to reduce the overall computational cost while maintaining accurate predictions. Furthermore, we propose a new framework for collaborating filtering in distributed recommendation systems that allows users to maintain their own rating profiles for privacy. We conduct offline and online tests of our ranking algorithm. We use Yahoo! Search queries that resulted in a click on a Yahoo! Movies or Internet Movie Database (IMDB) movie URL. Our online test involved 44 Yahoo! Employees providing subjective assessments of results quality. In both tests, our ranking methods show significantly better recall and quality than IMDB search and Yahoo! Movies current search. Reduced rank approximation of matrices has hitherto been possible only by un-weighted least squares. This paper presents iterative techniques for obtaining such approximations when weights are introduced. N� de r�f. du vendeur 9783656563242

Contacter le vendeur

Acheter neuf

EUR 15,95

EUR 60,23 shipping
Exp�dition depuis Allemagne vers Etats-Unis

Quantit� disponible : 1 disponible(s)

Ajouter au panier

Image fournie par le vendeur

Optimized Ranking-Based Techniques for Improving Aggregate Recommendation Diversity

Saravana Kumar

Edit� par GRIN Verlag, GRIN Verlag Dez 2013, 2013

ISBN 10 : 3656563241 ISBN 13 : 9783656563242

Neuf Taschenbuch

impression � la demande

Vendeur : BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Allemagne

�valuation du vendeur 5 sur 5 �toiles

Taschenbuch. Etat : Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Master's Thesis from the year 2013 in the subject Computer Science - Miscellaneous, grade: 1, , course: ME computer science, language: English, abstract: This paper investigates how demand-side factors contribute to the Internet's 'Long Tail' phenomenon. It first models how a reduction in search costs will affect the concentration in product sales. Then, by analyzing data collected from a multi-channel retailing company, it provides empirical evidence that the Internet channel exhibits a significantly less concentrated sales distribution, when compared with traditional channels. The difference in the sales distribution is highly significant, even after controlling for consumer differences. Furthermore, the effect is particularly strong for individuals with more prior experience using the Internet channel. We find evidence that Internet purchases made by consumers with prior Internet experience are more skewed toward obscure products, compared with consumers who have no such experience. We observe the opposite outcome when comparing purchases by the same consumers through the catalog channel. If the relationships we uncover persist, the underlying trends in technology and search costs portend an ongoing shift in the distribution of product sales. Singular Value Decomposition (SVD), together with the Expectation-Maximization (EM) procedure, can be used to find a low-dimension model that maximizes the log likelihood of observed ratings in recommendation systems. However, the computational cost of this approach is a major concern, since each iteration of the EM algorithm requires a new SVD computation. We present a novel algorithm that incorporates SVD approximation into the EM procedure to reduce the overall computational cost while maintaining accurate predictions. Furthermore, we propose a new framework for collaborating filtering in distributed recommendation systems that allows users to maintain their own rating profiles for privacy. We conduct offline and online tests of our ranking algorithm. We use Yahoo! Search queries that resulted in a click on a Yahoo! Movies or Internet Movie Database (IMDB) movie URL. Our online test involved 44 Yahoo! Employees providing subjective assessments of results quality. In both tests, our ranking methods show significantly better recall and quality than IMDB search and Yahoo! Movies current search. Reduced rank approximation of matrices has hitherto been possible only by un-weighted least squares. This paper presents iterative techniques for obtaining such approximations when weights are introduced. 20 pp. Englisch. N� de r�f. du vendeur 9783656563242

Contacter le vendeur