A methodology of generating customer satisfaction models for new product development using a neuro-fuzzy approach
A methodology of generating customer satisfaction models for new product development using a neuro-fuzzy approach
复制标题
DOI：
10.1016/j.eswa.2009.02.094
复制
发表时间：
2009-10
期刊：
影响因子：
--
通讯作者：
C. Kwong;T. C. Wong;Kit Yan Chan
中科院分区：
文献类型：
--
作者：
C. Kwong;T. C. Wong;Kit Yan Chan
在开发新产品时，设计团队了解消费者对消费产品的看法非常重要，因为此类产品的成功在很大程度上取决于相关的客户满意度水平。如果用户满意，新产品在市场上成功的机会就会更高。在这项研究中，提出了一种使用神经模糊方法生成客户满意度模型的新方法。与以往的研究相反，非线性和明确的客户满意度模型可以开发与使用所提出的方法。以笔记本电脑设计为例说明了该方法。采用统计回归的基准对所提出的方法进行了测量，以确定其有效性。实验结果表明，该方法在平均绝对误差和误差方差方面优于统计回归方法。
When developing new products it is important for design teams to understand customer perceptions of consumer products because the success of such products is heavily dependent upon the associated customer satisfaction level. The chance of a new product’s success in a marketplace is higher if users are satisfied with it. In this study, a new methodology of generating customer satisfaction models using a neuro-fuzzy approach is proposed. In contrast to previous research, non-linear and explicit customer satisfaction models can be developed with the use of the proposed methodology. An example of notebook computer design is used to illustrate the methodology. The proposed methodology was measured against the benchmark of statistical regression to determine its effectiveness. Experimental results suggested that the proposed approach outperformed the statistical regression method in terms of mean absolute errors and variance of errors.