摘要： It is often observed that consumers select the upper class brand when they buy the next time. Suppose that the former buying data and the current buying data are gathered. Also suppose that the upper brand is located upper in the variable array. Then the transition matrix becomes an upper triangle matrix under the supposition that the former buying variables are set input and the current buying variables are set output. If the top brand were selected from the lower brand in jumping way, corresponding part in the upper triangle matrix would be 0. A questionnaire investigation for automobile purchasing case is executed and the above structure is confirmed. If the transition matrix is identified, a S-step forecasting can be executed. Generalized forecasting matrix components’ equations are introduced. In this paper, brand bag purchasing case is considered and a method of building the ranking table by utilizing correspondence analysis is newly proposed. Unless planner for products does not notice its brand position whether it is upper or lower than another products, matrix structure make it possible to identify those by calculating consumers’ activities for brand selection. Thus, this proposed approach enables to make effective marketing plan and/or establishing new brand.
