Modeling Pricing Strategies Using Game Theory and Support Vector Machines ∗ † Cristi´ an Bravo, Nicol´ as Figueroa, and Richard Weber Department of Industrial Engineering Universidad de Chile {cbravo,nicolasf,rweber}@dii.uchile.cl Final version: 24 April 2010 Abstract Data Mining is a widely used discipline with methods that are heavily supported by statistical theory. Game theory, instead, develops models with solid economical foundations but with low applicability in companies so far. This work attempts to unify both approaches, presenting a model of price competition in the credit industry. Based on game theory and sustained by the robustness of Support Vector Machines to structurally estimate the model, it takes advantage from each approach to provide strong results and useful information. The model consists of a market- level game that determines the marginal cost, demand, and efficiency of the competitors. Demand is estimated using Support Vector Machines, allowing the inclusion of multiple variables and empowering standard eco- nomical estimation through the aggregation of client-level models. The model is being applied by one competitor, which created new business op- portunities, such as the strategic chance to aggressively cut prices given the acquired market knowledge. 1 Introduction Among the diverse decisions taken by companies, pricing is one of the most important. Decision makers do not only have a product’s or service’s price as a tool to affect demand, but also several marketing actions (e.g. mailings or call * The following is a self-archive version of the paper published at ICDM 2010 conference in Berlin, Germany. The original publication is available at www.springerlink.com, in particular http://www.springerlink.com/content/g728865818w8217g/. † Please cite this paper as follows: C. Bravo, N. Figueroa, and R. Weber. Modeling pricing strategies using game theory and support vector machines. In Petra Pertner, editor, Advances in Data Mining. Applications and Theoretical Aspects, Lecture Notes in Computer Science 6171, pages 323-337, 2010. 1