An Agent-Based Architecture for the Decision Support Process

摘要

Firms require a control mechanism that facilitate the analysis of work carried out inchanging environments, such as finance. A tool for the decision support process has been de-veloped based on a multi-agent system that incorporates a case-based reasoning system. Thecase-based reasoning system automates the process of case indexing and retrieval by means of aMaximum Likelihood Hebbian Learning-based method. The multi-agent system has been testedwithin ten small and medium companies and the results obtained have been very satisfactory.