Study On The Methods For Multiple Attribute Decision Making Considering Decision Maker’s Psychological Behavior

Multiple attribute decision making (MADM) refers to the problem of selecting among alternatives considering multiple attributes. It is a problem with extensive theoretical and practical backgrounds in the fields of economics, management, and engineering. Most of the traditional multiple attribute decision theory and methods are based on expected utility theory, which requires a strict assumption that the decision maker (DM) is completely rational. The DM can get all the information that he/she needs for making decisions, and the DM can also use the information to make optimal decisions. However, much existing empirical study shows that the DM’s actural decision behavior in the process of decision making violates from the assumption that the DM is completely rational, which indicates that the DM is bounded rationality rather than perfect rationality when he/she makes decisions. Thus, most of the existing MADM methods cannot be used to solve the MADM problem in which the DM’s psychological behavior is considered. Currently, MADM problem considering DM’s psychology behavior has attracted the attention of some scholars and several research results have been proposed. However, few studies have been conducted to develop scientific and effective decision methods for solving the MADM problem considering DM’s psychological behavior. Therefore, it is of great important theoretic and practical significance to summarize the MADM problem considering DM’s psychological behavior and propose targeted methods for the problem.The purpose of this thesis is to study the MADM problem in which the DM’s psychological behavior is considered. With regard to the limitations of the existing research, a serious of research works is conducted and the contributions are as follows.First, typical MADM problems considering DM’s psychological behavior are extracted. According to the practical backgrounds of MADM problem in which DM’s psychological behavior is considered, typical MADM problems considering DM’s psychological behavior are extracted in this thesis, and the problems are classified into two categories, i.e., the MADM problem with DM’s aspiration information and the MADM problem without DM’s aspiration information.Second, with regard to the MADM problem with DM’s aspiration information, a method considering DM’s psychological behavior is proposed. For research about this problem, the description of the MADM problem with DM’s aspiration information and the research frame of this problem are given firstly. Then, considering the decision maker’s psychological behavior, such as reference dependence, loss aversion, diminishing sensitivity, a hybrid MADM method based on cumulative prospect theory is proposed.Third, with regard to the MADM problem without DM’s aspiration information, a method considering DM’s psychological behavior is proposed. For research about this problem, the description of the MADM problem without DM’s aspiration information and the research frame of this problem are given firstly. Then, considering the decision maker’s psychological behavior, such as reference dependence, loss aversion, diminishing sensitivity, a hybrid MADM method based on TODIM is proposed.Fourth, the application research of the methods proposed in this thesis in the stock investment decision analysis is given. Taking the stock investment decision analysis as an example, the feasibility and reasonability of the methods are verified.The proposed method can not only be used to solve the stock investment decision problem, but also be used to solve some other practical problems, such as new product development, route choice, revenue management and medical decision making. This thesis provides a theoretical guidance framework and analysitcal framework to the study of MADM problem considering DM’s psychological behavior, and also lays a solid foundation to the extension and application of the related study.