Family Clothing Consumer Decision-making Behavior Of The System Integration Model And Its Market Applications

The fundamental theoretical framework of this dissertation is the "Stimulus-Response" Model of psychological behaviorism .The author applies this model into the apparel-buying behavior and proposes the "Systematical Integrated Model" in the apparel consumption decision-making. The author tends to find out the correspondent relationship between the different buying behaviors and their characteristics through the newest technique of data mining-- Hybrid Machine Learning (HML). Therefore, three sub-models on apparel consumption will be established. They are the model of "The Product and Quantity Choice", of " The Store Choice Preference" and of "The Payer Probability" in Shanghai. Then the Systematical Integrated Model in apparel consumption decision-making of Shanghai household will be drawn. In further, the author applies this integrated model into the real market analysis, in which price preference was used as the index to segment the apparel market. In addition, the different segmentation's characteristic and its corresponding store preference and payer probability will be described, and the market capacity forecasted as well.Hybrid Machine Learning (HML) is the latest applying in the field of intelligent information process. It combines the induced learning based-on decision-making tree with the blocking neural network. And it provides a useful intelligent knowledge-based data mining technique. Its core arithmetic is I D3 and FTART.To guarantee the sample data as science, entireness, typical, and accurate, the author selected the samples from the investigating network of Shanghai Statistic Bureau, which were composed of 300 households in total and 292 effective samples were defined finally. The research lasted a period of one year and data collected within each season. During this period, area selecting, sampling, interviewertraining, pilot testing and questionnaire revising were took action to ensure the quality of the research. Then the author established the database on the requirements of HML and used it to analysis the Shanghai household' s apparel consumption decision-making behavior and its influencing factors. In the study, the apparel is classified into 12 categories. They are underwear, T-shirt, sweater, shirt, denim wear, suit, casual wear, coat, sportswear, trousers/skirts, accessories and fabrics.Although the studies about apparel expenditure in the world have reached a high level, it has still rare research in this field by data mining technique. Surely, it brings more difficulties to finish the research, but it endues the prominent significance of solving the social problem with nature science methodology.In short, the innovations of this research can be concluded as foMowings: (1) to take the lead in applying the newest data mining technique based-on the artificial intelligence in the traditional apparel expenditure behavior, which is not only unique in angle of view but also creative in the research methodology; (2) to integrate each aspect of the household apparel consumption decision-making behavior within one system, then to apply the outcome into market practice; (3) to take use of both the traditional statistic methods and data mining technique based-on HML to analysis apparel consumption decision-making behavior, which learn from others' strong points to offset one's weakness and achieve mastery through a comprehensive study of the subject.