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 cus-tomers 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 pre-diction errors and recommended sample votes between the novel and conventional ap-proaches 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.