Global Business and Economics Review, Vol. 11, No. 1, 2009 1 Copyright © 2009 Inderscience Enterprises Ltd. An evaluation of UK risky money: an artificial intelligence approach Jane M. Binner* Economics and Strategy Group Aston Business School Birmingham, B4 7ET, UK E-mail: j.m.binner@aston.ac.uk *Corresponding author Alicia M. Gazely Department of Information Management & Systems The Nottingham Trent University Nottingham, NG1 4BU, UK E-mail: alicia.gazely@ntu.ac.uk Graham Kendall School of Computer Science Jubilee Campus The University of Nottingham Nottingham, NG8 1BB, UK E-mail: gxk@cs.nott.ac.uk Abstract: In this paper we compare the performance of three indices in an inflation forecasting experiment. The evidence not only suggests that an evolved neural network is superior to traditionally trained networks in the majority of cases, but also that a risky money index performs at least as well as the Bank of England Divisia index when combined with interest rate information. Notably, the provision of long-term interest rates improves the out-of-sample forecasting performance of the Bank of England Divisia index in all cases examined. Keywords: risky money; artificial intelligence: forecasting; neural networks: evolution strategies. Reference to this paper should be made as follows: Binner, J.M., Gazely, A.M. and Kendall, G. (2009) ‘An evaluation of UK risky money: an artificial intelligence approach’, Global Business and Economics Review, Vol. 11, No. 1, pp.1–18. Biographical notes: Jane M. Binner applies traditional methods such as investment appraisal analysis and also state-of-the-art modelling methods such as dynamic game theory modelling. Her work centres on the application of advanced multivariate techniques to a range of data types, particularly the econometric and time series analysis of financial data. The work, which is