International Environmental Modelling and Software Society (iEMSs) 2010 International Congress on Environmental Modelling and Software Modelling for Environment’s Sake, Fifth Biennial Meeting, Ottawa, Canada David A. Swayne, Wanhong Yang, A. A. Voinov, A. Rizzoli, T. Filatova (Eds.) http://www.iemss.org/iemss2010/index.php?n=Main.Proceedings Evolving GESCONDA to an Intelligent Decision Support Tool Miquel Sànchez-Marrè a,b , Karina Gibert a,c , Beatriz Sevilla a,b a Knowledge Engineering and Machine Learning Group (KEMLG) b Computer Software Dept. c Statistics and Operations Research Dept. Universitat Politècnica de Catalunya-BarcelonaTech, Barcelona, Catalonia (miquel@lsi.upc.edu, karina.gibert@upc.edu, bea.sevilla@gmail.com) Abstract: In this work, the GESCONDA system is presented. Initially it was conceived as a system for knowledge discovery and Data Mining, but currently, the system supports two new functionalities. A case-based reasoning engine and a rule-based reasoning shell are provided. These new skills of GESCONDA makes it a suitable prototype tool for the deployment of Intelligent Decision Support Systems, including all main steps like data preparation and filtering, data mining, model validation, reasoning abilities to generate solutions, and predictive models to support final users. The purpose of the paper is to present its architecture as well as its functionalities. Keywords: Intelligent Decision Support Tools; Intelligent Data Analysis; Environmental Systems 1. INTRODUCTION The main goal of this research is to design and develop a tool, named GESCONDA, for intelligent data analysis and management of implicit knowledge from databases and also for providing the users with reasoning capabilities, with special focus on environmental databases and environmental modelling. The latter is remarkable due to the high amount and high heterogeneous data in the environmental field. It will provide support to knowledge discovery and data mining to obtain valid new knowledge as well as to solving tasks and predictive tasks using the obtained knowledge/models to guide the decision- making process. Although in the literature other knowledge discovery tools or commercial systems exist, but none of them strongly integrates statistical and machine learning methods together nor integrates the problem solving and predictive skills in the same tool. Besides the possibility of explicit management of the produced knowledge in Knowledge Bases or Case Bases, the tool also shows other abilities. There are mixed techniques that can cooperate among them to discover and extract the knowledge contained in data allowing interaction among all methods, and the existence of a recommender agent, which will suggest the best method to be used depending on the target domain and on the goals specified by users. The GESCONDA tool has been successfully used in the partial development of IEDSS in several environmental domains (see Sànchez-Marrè and Gibert [2008] or Sànchez-Marrè et al. [2004]). 1.1 Related Work Intelligent artificial applications that support decision-making processes and problem- solving activities have proliferated and evolved over the past decades. Nowadays, there is a wide range of applications both from the commercial and academic source. One of the most