Fashion perceptual data mining based on clustering algorithm

The paper collected consumers preference rates of all related design elements through questionnaires,and made discrete design elements correspondent to fashion perceptual data information and then conducted quantization. And based on it,the consumers perceptual intention matrix was designed. Having normalized the matrices data, K-means clustering algorithm was used for data processing through WEKA,a professional data mining software. Finally,in accordance with the output data,four typical design models was built to carry out scientifical analysis and procession of the perceptual preferences of most consumers and obtain,through fitting the best design model which is typical and can guide fashion perceptual desinging work. Through the method of the present study,it can reveal the preference degree of different types of consumer effectively,and screen out the important design elements with positive impact on consume behavior,and provide reference to fashion designers.