IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
... (for ESS/CS/ES/ISS)
Tech. Rep. Archives
... (for ES/CS)
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2014-03-06 14:55
Consideration of Correlation between Users' Evaluating Values and Their Dropouts in Missing Value Prediction
Kenta Nishimura, Toshiyuki Tanaka (Kyoto Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) In user-item relational data, there are sometimes correlations between values and their dropouts. Existing methods under consideration of such correlations can treat only objective or discrete values, and are unsuited for data of subjective and continuous values in which users’ scale of values may differ. As for the different scales, it is natural to do user normalization, which equalize users’ scales. However, if dropouts correlate with unseen values, we need to accomplish user normalization considering the correlations. Assuming dropouts depend on unseen values, we propose a new user normalization method and collaborative filtering method which can deal with continuous values and which is based on matrix factorizations. As for the latter method, rigorous calculation is intractable, and therefore we also propose an approximate method on the basis of variational Bayesian framework.
Keyword (in Japanese) (See Japanese page) 
(in English) missing value prediction / collaborative filtering / missing not at random / user normalization / Bayesian matrix factorization / variational Bayes / /  
Reference Info. IEICE Tech. Rep., vol. 113, no. 476, IBISML2013-71, pp. 31-38, March 2014.
Paper # IBISML2013-71 
Date of Issue 2014-02-27 (IBISML) 
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380

Conference Information
Committee IBISML  
Conference Date 2014-03-06 - 2014-03-07 
Place (in Japanese) (See Japanese page) 
Place (in English) Nara Women's University 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Statistical mathmatics, machine learning, data mining, and other topics 
Paper Information
Registration To IBISML 
Conference Code 2014-03-IBISML 
Language English (Japanese title is available) 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Consideration of Correlation between Users' Evaluating Values and Their Dropouts in Missing Value Prediction 
Sub Title (in English)  
Keyword(1) missing value prediction  
Keyword(2) collaborative filtering  
Keyword(3) missing not at random  
Keyword(4) user normalization  
Keyword(5) Bayesian matrix factorization  
Keyword(6) variational Bayes  
Keyword(7)  
Keyword(8)  
1st Author's Name Kenta Nishimura  
1st Author's Affiliation Kyoto University (Kyoto Univ.)
2nd Author's Name Toshiyuki Tanaka  
2nd Author's Affiliation Kyoto University (Kyoto Univ.)
3rd Author's Name  
3rd Author's Affiliation ()
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker
Date Time 2014-03-06 14:55:00 
Presentation Time 25 
Registration for IBISML 
Paper # IEICE-IBISML2013-71 
Volume (vol) IEICE-113 
Number (no) no.476 
Page pp.31-38 
#Pages IEICE-8 
Date of Issue IEICE-IBISML-2014-02-27 


[Return to Top Page]

[Return to IEICE Web Page]


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan