An intelligent advisor to suggest strategies in economic policy decisions

In this paper we illustrate the architecture of an agent that plays the role of an "intelligent advisor". The advisor is aimed at suggesting the best managing strategies for a model of a virtual town. A Decision Support System (DSS) embedded on a conversational agent constitutes the intelligent advisor architecture. Two interacting knowledge representation areas characterize the DSS. The first one deals with the description of the domain and the deterministic events through the use of ontologies. The second one deals with the management of situations characterized by uncertainty. The intelligent advisor tries to prospect the future evolutions of particular choices taken by the user, and as a consequence, suggests the player-user the best strategy given the current status of the game. © 2010 IEEE.