Beschreibung:
With changing customer attitudes toward consumption and function homogenization, product appearance designs have an increasing influence on the purchase decision. Customer characteristics and emotional factors play an important role here. This study proposes a novel approach for modelling satisfaction and accomplishing a configuration that overcomes the limitations of conventional methods to precisely predict satisfaction, provide optimal product recommendations, and advise manufacturers on product appearance design. The newly proposed approach considers satisfaction, clusters customers through the Kansei perspective, and constructs a satisfaction model for each cluster. Additionally, the study employs data mining to understand the basic design principles and conflicted combinations that must be followed and avoided, respectively. The bidirectional association rules-constrained genetic algorithm is presented to limit configuration freedom, ensuring that results are in the range of control. Comparing prediction errors and recommended sample votes between the novel and conventional approaches revealed the presented approach’s efficiency and accuracy, thereby providing suggestions for manufacturers to make precise decisions on launching new product appearance designs through predicting customer emotional satisfaction.