Extended QFD and data-mining-based methods for supplier selection in mass customization

Abstract

In mass customization, different kinds of customer requirements should be satisfied by the manufacturer. Supplier selection is one important task in supply-chain management. Effective supplier selection calls for robust analytical methods and decision-support tools. This research aims to develop a supplier selection methodology based on extended quality function deployment (QFD) and data-mining (DM) techniques. Through considering customer requirement and performance of components in a product's full life-cycle, the manufacturer can use data-mining techniques to find out quality requirements correlated to customer categories, product usage patterns, and frequent fault patterns in order to select the proper combination of suppliers. In this way, the manufacturer can decrease costs, raise product quality, and improve customer satisfaction. Related data-mining algorithms for supplier selection are presented. Customer requirement analysis is also studied in the paper, and transcendental and empirical customer requirement analysis methods are put forward. A case study is provided in detail. Finally, as a part of the supply-chain management system, a supplier selection prototype system is designed and implemented. Evaluation of experiments in an automobile manufacturing enterprise verifies the feasibility and efficiency of our method.

Keywords:

• Supply-chain management
• Mass customization
• Supplier selection
• Quality-function deployment
• House of quality
• Data mining

Acknowledgements

This work is supported by the National High-Tech Research and Development Program of China under Grant No. 2003AA413021, 2003AA4Z3370, 2002AA413310, and the National Natural Science Foundation of China (Grant No. 60084004).