Modeling the Firm as an Artificial Neural Network * Jason Barr Department of Economics Rutgers University Newark, NJ 07102 USA Ph: 973-353-5835 Fax: 973-353-5819 jmbarr@rutgers.edu and Francesco Saraceno Observatoire Français des Conjonctures Économiques 69 Quai d'Orsay, 75007 Paris, France Ph: +33-1-44-18-54-93 Fax: +33-1-44-18-54-88 francesco.saraceno@sciences-po.fr October 15, 2005 Abstract: The purpose of this chapter is two-fold: (1) to make the case that a standard backward propagation artificial neural network (ANN) can be used as a general model of the information processing activities of the firm, and (2) to present a synthesis of Barr and Saraceno (BS) (2002, 2004, 2005), who offer various models of the firm as an artificial neural network. JEL Classification: C63, D21, D83, L13 Keywords: Artificial neural networks, information processing, firm learning, agent-based Rutgers University Newark Working Paper #2005-011