Using Neural Network and Piecewise Regression to Analyze Two-Dimensional Quality Model

• Main Authors: HSIAO, YIN-CHENG, 蕭銀城
• Other Authors: LEE, YU-CHENG
• Format: Others
• Language: zh-TW
• Published: 2014
• Online Access: http://ndltd.ncl.edu.tw/handle/w93jvt

博士 === 中華大學 === 科技管理博士學位學程 === 103 === Kano’s model of two-dimension quality can display the correlation between the actual quality performance and customer satisfaction, and has been widely applied in various fields, and also its efficient integration with other quality management methods. Since its introduction, many different methods have been proposed to improve the original model. However, too little attention is paid to the development of the Kano’s model or the design of new methods to replace the original evaluation table. Most of the existing methods are based on the operational validity and cannot fully reflect the non-linear relationship between the quality attributes and customer satisfaction. In addition, one-dimension quality model might underestimate the attractive quality attributes but overestimate the must-be quality and indifferent quality attributes. In this study, we propose a modified evaluation sheet of Kano’s model. Funeral Service Providers in Taipei City are investigated and its customer satisfaction. And then applying Artificial Neural Network (ANN) and Piecewise Regression to be analysis and verified. The result is found that, we propose an enhanced quality model to clarify the correlation between quality attributes and customer satisfaction. Moreover, the priorities of quality improvement should be decided for optimizing customer satisfaction. Through our case study, the proposed enhanced quality model is proved to be feasible and valid.