4.1 Defining the problem for data mining
Owing to unknown weights for future CRs, a large marketing database was created by a professional computer manufacturer in Taiwan, based on many sales questionnaries, according to four period questionnaires; this resulted in a huge amount of data. The intent of this study was to explore and analyze a huge amount of data, by employing a time series-based data mining cycle in QFD, so as to identify the weights within customer questionnaires in each period. Based on these the weights of CRs, the future CRs for dynamic forecasting of life cycle under green supply chain may be discovered and the results can be encouraged and beneficial the computer designers and manufacturers.