J.M.C. Rodríguez et al. (Eds.): Trends in PAAMS, AISC 157, pp. 49–56. springerlink.com © Springer-Verlag Berlin Heidelberg 2012 Improving Production in Small and Medium Enterprises María L. Borrajo, Javier Bajo, and Juan F. De Paz * Abstract. Knowledge management has gained relevance during the last years to improve business functioning. However, there is still a growing need of developing innovative tools that can help small to medium sized enterprises to detect and predict undesired situations. This article present a multi-agent system aimed at detecting risky situations. The multi-agent system incorporates models for reasoning and makes predictions using case-based reasoning. The models are used to detect risky situations and an providing decision support facilities. An initial prototype was developed and the results obtained related to small and medium enterprises in a real scenario are presented. Keywords: Hybrid neural intelligent system, CBR, MAS, Business Intelligence, business risk prediction. 1 Introduction Knowledge Management is a fundamental asset for businesses in the contemporary economy. Knowledge takes into account the organization of the María L. Borrajo Dept. Informática, University of Vigo, Campus Universitario As Lagoas s/n, Ourense, 32004, Spain e-mail: lborrajo@uvigo.es Javier Bajo Facultad de Informática, Universidad Pontificia de Salamanca, Compañía 5, 37002, Salamanca, Spain e-mail: jbajope@upsa.es Juan F. De Paz Departamento Informática y Automática Universidad de Salamanca, Plaza de la Merced s/n, 37008, Salamanca, Spain e-mail: fcofds@usal.es