The user portraits of offline shopping malls and Internet platforms are more about analyzing the demographic attributes and behavioral characteristics of users, so as to provide better shelf arrangement or more accurate content push. In early market research, marketers often need to understand users through user surveys and interviews, but after the rapid growth of the number of users in the big data era, the efficiency of the survey has decreased, which requires the use of user portraits to cooperate with research.
As a platform, Amazon has also launched a user-based collaborative filtering algorithm, which has become an important part of the A9 algorithm. But for Amazon brand sellers, especially sellers in the clothing category, the main purpose of user portraits is to assist operations and product selection. Although the data obtained is not so perfect, sellers can organize user portraits according to the actual business situation through order reports and Amazon’s in-site information to ensure business relevance
In actual early operations, sellers do not need a perfect user portrait. Because clothing is a strong cyclical product, as long as sellers obtain some relatively accurate user portrait information, they can immediately start product selection and operation, and then verify whether the user portrait is correct through the market. After a period of operation, the accuracy of user portraits can be significantly improved.