Decision Support An action learning approach for assessing the consistency of pairwise comparison data Kweku-Muata Osei-Bryson * Department of Information Systems & The Information Systems Research Institute, Virginia Commonwealth University, Richmond, VA 23284, USA Received 24 July 2003; accepted 20 January 2005 Available online 23 May 2005 Abstract Pairwise comparison data are used in various contexts including the generation of weight vectors for multiple criteria decision making problems. If this data is not sufficiently consistent, then the resulting weight vector cannot be consid- ered to be a reliable reflection of the evaluatorÕs opinion. Hence, it is necessary to measure its level of inconsistency. Different approaches have been proposed to measuring the level of inconsistency, but they are often based on Ôrules of thumb’’ and/or randomly generated matrices, and are not interpretable. In this paper we present an action learning approach for assessing the consistency of the input pairwise comparison data that offer interpretable consistency measures. Ó 2005 Published by Elsevier B.V. Keywords: Pairwise comparisons; Consistency indicators; Inconsistency; AHP; Interpretability; Multiple criteria decision making; Goal programming 1. Introduction Pairwise comparison data are used in various contexts such as the generation of weight vectors for multi- ple criteria decision making problems (e.g. Ngai, 2003; Saaty, 1980), subjective probabilities for expert sys- tems (e.g. Monti and Carenini, 2000), and Dempster–Shafer belief functions (e.g. Bryson and Mobolurin, 1999). The pairwise comparison information is represented numerically using an N · N matrix A ={a ij }, where a ij is a non-negative rational number (e.g. 0.90) that is the numerical equivalent of the comparison 0377-2217/$ - see front matter Ó 2005 Published by Elsevier B.V. doi:10.1016/j.ejor.2005.01.061 * Tel.: +1 804 827 3632; fax: +1 804 828 3199. E-mail address: kweku.muata@isy.vcu.edu European Journal of Operational Research 174 (2006) 234–244 www.elsevier.com/locate/ejor