Paper Info
Title
A forward selection based fuzzy regression for new product development that correlates engineering characteristics with consumer preferences.
Abstract
Fuzzy regression models have commonly been used to correlate engineering characteristics with consumer preferences regarding a new product. Based on the models, product developers can determine optimal engineering characteristics of the new product in order to satisfy consumer preferences. However, they have a common limitation in that they cannot guarantee to include significant regressors with significant engineering characteristics or significant nonlinear terms. The generalization capability of the model can be reduced, when too few significant regressors are included and too many insignificant regressors are included. In this paper, a forward selection based fuzzy regression (FS-FR) is proposed based on the statistical forward selection to determine significant regressors. After the significant regressors are determined, the fuzzy regression is used to generate the fuzzy coefficients which address the uncertainties due to fuzziness and randomness caused by consumer preference evaluations. The developed model includes only significant regressors which attempt to improve the generalization capability. A case study of a tea maker design demonstrated that the FS-FR was able to generate consumer preference models with better generalization capabilities than the other tested fuzzy regressions. Also simpler consumer preference models can be provided for the new product development.
Year
DOI
Venue
2016
10.3233/IFS-151898
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
Keywords
Field
DocType
Fuzzy regression,statistical forward selection,new product development,consumer preferences,engineering characteristics,tea maker design,overfitting,generalization capability
Nonlinear system,Fuzzy logic,Fuzzy regression,Artificial intelligence,Forward selection,Machine learning,Mathematics,Randomness,New product development
Journal
Volume
Issue
ISSN
30
3
1064-1246
Citations 
PageRank 
References 
3
0.39
12
Authors
2
Name
Order
Citations
PageRank
Kit Yan Chan147045.36
Sai-Ho Ling217925.93