Implementing a Rule based Decision Support Mechanism for Selecting Alternatives

Abstract

The importance of aids for decision making is widely recognized in social activities. The well-known model of decision making processes proposed by Simon provides a useful framework for designing an effective mechanism for aiding decision making. In the model, we focus on the design phase and the choice phase to support decisions for selecting alternatives. We propose a system for aiding the decisions in which the system manages subjective judgments by a decision maker and they are used to select alternatives effectively. We call the system CDSS (Choice Design Support System). CDSS helps decision maker make a reasonable choice from alternatives by structuring his knowledge and extracting his subjective judgments. In the choice process, two processes are used. One is a process which clarifies attributes used for estimating the alternatives. The other is a process which determines the priorities of the alternatives by estimating the attributes. In the estimation, a pairwise comparison method based on AHP (Analytic Hierarchy Process) is used. The main advantages of CDSS can be described as follows : (l) CDSS provides functions for realizing flexible pairwise comparisons in which a decision maker can represent his belief for the comparisons. (2) CDSS can dynamically manage the order of the comparisons in which some redundant pairwise comparisons are omitted. This feature contributes to avoiding tedious comparisons. (3) The consistency of the comparisons are dynamically checked by using a TMS-based mechanism in the production system KORE/IE. This paper gives a method for implementing the functions for CDSS by using rule-based programming. CDSS is realized on KORE/IE which is implemented on PSI machine developed by ICOT.