A Precise Identification and Matching Method for Customer Needs Based on Sales Data

Abstract

In the stage of product design, it is very helpful to understand customer needs accurately to improve product performance. The current customer needs identification scheme cannot meet the dynamic and precise characteristics of customer needs. A precise identification architecture of customer demand based on online sales data and probability theory is proposed. Online sales data provide potential customer demand information, the data is used to build the relationship between customer satisfaction and product function. Vector similarity is used to match user needs and product functions. At the same time, a ranking method of product satisfaction recommended to users is proposed by using the concepts of probability and statistics. The characteristic of this method is that it can feedback user’s needs in real time. The customer eventually gets a product that meets the demand and the customer is most satisfied with the product. Finally, this paper demonstrates the implementation process of this method by taking the multi-functional desk as an example.