Title :
Requirement-driven decision support systems
Author :
Rubin, Stuart H.
Author_Institution :
Dept. of Comput. Sci., Central Michigan Univ., Mount Pleasant, MI, USA
Abstract :
It is argued that one of the problems associated with contemporary rule-based decision-support systems is that it is not always practical to specify completely a consistent set of decision rules. However, in these cases it is often possible to specify qualitative features (including constraints) and a performance critique for use in the genetic evolution of a consistent set of decision rules. In particular, the author integrates previous research to yield a genetic expert system, i.e., an expert system whose rule base may be formulated as a high-level constraint-satisfaction problem
Keywords :
decision support systems; expert systems; optimisation; genetic evolution; genetic expert system; high-level constraint-satisfaction problem; performance critique; qualitative features; requirement-driven decision support systems; rule-based DSS; Computer science; Decision support systems; Expert systems; Feedback; Genetics; Investments; Knowledge engineering; Large-scale systems; Spread spectrum communication; Stock markets;
Conference_Titel :
Systems, Man and Cybernetics, 1989. Conference Proceedings., IEEE International Conference on
Conference_Location :
Cambridge, MA
DOI :
10.1109/ICSMC.1989.71448