Applying Genetic Programming in Business Forecasting

Since the global recession of 2008–2009, it has been much more widely understood that reliable economic forecasting is needed in business decision-making. Of special interest are the forecasting methods based on explanatory variables (economic drivers), the most popular of which is the Auto-Regressive Integrated Moving-Average with eXplanatory variables (ARIMAX) model. A limitation of this approach, however, is the assumption of linear relationships between the explanatory variables and the target variable. Genetic programming is a potential solution for representing nonlinearity and a hybrid scheme of integrating static and dynamic nonlinear transforms into the ARIMAX models is proposed in the chapter. From an implementation point of the view the proposed solution has several advantages, such as: optimal synergy between two well-known approaches like GP and ARIMAX, avoiding the need for developing a solid theoretical alternative for nonlinear time series modeling, using available forecasting software, and low efforts to train the final user. The proposed approach is illustrated with two examples from real business applications in the area of raw materials forecasting.

[1]  Dafydd Gibbon,et al.  1 User’s guide , 1998 .

[2]  A. Brabazon,et al.  An Introduction to Evolutionary Computation in Finance , 2008, IEEE Computational Intelligence Magazine.

[3]  Chip Wells,et al.  Applied Data Mining for Forecasting Using SAS , 2012 .

[4]  Arthur K. Kordon,et al.  Genetic Programming Transforms in Linear Regression Situations , 2011 .

[5]  Arthur K. Kordon.  Hybrid intelligent systems for industrial data analysis , 2004 .

[6]  Arthur K. Kordon,et al.  Variable Selection in Industrial Datasets Using Pareto Genetic Programming , 2006 .

[7]  Arthur K. Kordon,et al.  Applying Computational Intelligence - How to Create Value , 2009 .

[8]  Zbigniew Michalewicz,et al.  Time Series Forecasting for Dynamic Environments: The DyFor Genetic Program Model , 2007, IEEE Transactions on Evolutionary Computation.

[9]  Steven C. Wheelwright,et al.  Forecasting methods and applications. , 1979 .

[10]  Mak A. Kaboudan,et al.  Forecasting with computer-evolved model specifications: a genetic programming application , 2003, Comput. Oper. Res..

[11]  Alan Pankratz,et al.  Forecasting with Dynamic Regression Models: Pankratz/Forecasting , 1991 .

[12]  M. A. Wincek.  Forecasting With Dynamic Regression Models , 1993 .

[13]  Mark Kotanchek,et al.  Pareto-Front Exploitation in Symbolic Regression , 2005 .

[14]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[15]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[16]  Peter E. Kennedy.  A Guide to Econometrics , 1979 .

[17]  Lee-Ing Tong,et al.  Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming , 2011, Knowl. Based Syst..

[18]  Terence Soule,et al.  Genetic Programming: Theory and Practice , 2003 .

[19]  Michael P. Clements,et al.  Forecasting economic and financial time-series with non-linear models , 2004 .