In the fashion industry, the new product development process is considered as a powerful tool that supports companies to survive and achieve greater success in dynamic markets. This study aims to create a predictive model that utilizes data mining techniques to identify the factors that influence customer behavior and estimate their clothing purchase preferences in this process.
This paper first determined the relationship between the product’s material and prices based on customers’ viewpoints through the K-means clustering technique. In the next step, customers’ preferences were measured through these fashion product’s attributes including colors, forms, styles and patterns by Conjoint analysis.
By collecting and analyzing data from markets and customers, reliable suggestions were proposed for designing garments that satisfy customers’ demands and raise company profits. These results from the forecasting model could support managers in making the best decisions, being time efficient and saving costs during the new product development process.
This study describes a new understanding of the elements influencing consumers’ behavior that are connected to fashion products. The incorporation of market data and scientific knowledge will improve the success of the new product development process.
