Aiming at the problem of portrait of members in shopping malls, this paper analyzes the similarities and differences of consumption behaviors between member groups and nonmember groups, and constructs the LRFMC model with k -means algorithm to analyze the value of membership. Second, active states of members are divided according to the consumption time interval, and KNN algorithm model is established to predict member states and used to predict the membership status. Finally, it discusses which types of goods are more suitable for promotional activities and can bring more profits to the shopping mall. [ABSTRACT FROM AUTHOR]