Neural Networks and Genetic Algorithms as Forecasting Tools: A Case Study on German Regions

This paper develops and applies neural network (NN) models to forecast regional employment patterns in Germany. Computer-aided optimization tools that imitate natural biological evolution to find the solution that best fits the given case (namely, genetic algorithms, GAs) are also used to detect the best NN structure. GA techniques are compared with more ‘traditional’ techniques which require the supervision of experienced analysts. We test the performance of these techniques on a panel of 439 districts in West and East Germany. Since the West and East datasets have different time spans, the models are estimated separately for West and East Germany. The results show that the West and East NN models perform with different degrees of precision, mainly because of the different time spans of the two datasets. Automatic techniques for the choice of the NN architecture do not seem to outperform selection procedures based on the supervision of expert analysts.

[1]  Stephen Taylor,et al.  Forecasting Economic Time Series , 1979 .

[2]  Uwe Blien,et al.  Forecasting Regional Employment with the ENTROP Method , 2001 .

[3]  A. Lapedes,et al.  Nonlinear signal processing using neural networks: Prediction and system modelling , 1987 .

[4]  J. Stock,et al.  A Comparison of Linear and Nonlinear Univariate Models for Forecasting Macroeconomic Time Series , 1998 .

[5]  Paul Krugman,et al.  Space: The Final Frontier , 1998 .

[6]  Manfred M. Fischer,et al.  Methodological Challenges in Neural Spatial Interaction Modelling: The Issue of Model Selection , 2000 .

[7]  Uwe Blien,et al.  Wage Curve Analyses of Establishment Data from Western Germany , 2001 .

[8]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[9]  Thomas Riechmann.  Learning in Economics , 2001 .

[10]  Manfred M. Fischer,et al.  Computational Neural Networks — Tools for Spatial Data Analysis , 2001 .

[11]  Peter Nijkamp,et al.  A Comparative Analysis of the Performance of Evolutionary Algorithms and Logit Models in Spatial Networks , 2000 .

[12]  Peter Nijkamp,et al.  Forecasting Regional Labour Markets in Germany An Evaluation of the Performance of Neural Network Analysis , 2002 .

[13]  D. M. Titterington,et al.  Neural Networks: A Review from a Statistical Perspective , 1994 .

[14]  Michael T. Manry,et al.  Convergent design of a piecewise linear neural network , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[15]  Peter Nijkamp,et al.  New advances in spatial network modelling: Towards evolutionary algorithms , 2001, Eur. J. Oper. Res..

[16]  J. Scott Armstrong,et al.  Research Report - Principles for Examining Predictive Validity: The Case of Information Systems Spending Forecasts , 1994, Inf. Syst. Res..

[17]  Jos Nijhuis,et al.  Neural network approaches to capture temporal information , 2001 .

[18]  Norman R. Swanson,et al.  Forecasting economic time series using flexible versus fixed specification and linear versus nonlinear econometric models , 1997 .

[19]  Manfred M. Fischer.  Computational Neural Networks:An attractive class of mathematical modelsfor transportation research , 1997 .

[20]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[21]  J. Keith Ord,et al.  Automatic neural network modeling for univariate time series , 2000 .

[22]  E. Lehmann,et al.  Nonparametrics: Statistical Methods Based on Ranks , 1976 .

[23]  Peter Nijkamp,et al.  Neural Network Modeling as a Tool for Forecasting Regional Employment Patterns , 2005 .

[24]  Bruce D. Baker,et al.  A comparison of conventional linear regression methods and neural networks for forecasting educational spending , 1999 .

[25]  Lawrence F. Katz,et al.  Regional Evolutions , 2007 .

[26]  M M Fischer.  COMPUTATIONAL NEURAL NETWORKS: AN ATTRACTIVE CLASS OF MATHEMATICAL MODELS FOR TRANSPORTATION RESEARCH. IN: NEURAL NETWORKS IN TRANSPORT APPLICATIONS , 1998 .

[27]  Alfredo Vellido,et al.  Neural networks in business: a survey of applications (1992–1998) , 1999 .

[28]  Halbert White,et al.  Artificial neural networks: an econometric perspective ∗ , 1994 .

[29]  Greg Tkacz.  Neural network forecasting of Canadian GDP growth , 2001 .

[30]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[31]  Guoqiang Peter Zhang,et al.  An investigation of neural networks for linear time-series forecasting , 2001, Comput. Oper. Res..

[32]  David E. Rumelhart,et al.  Predicting the Future: a Connectionist Approach , 1990, Int. J. Neural Syst..

[33]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[34]  Antonio Fatás,et al.  Regional labor market dynamics in Europe , 1995 .

[35]  John C. B. Cooper.  Artificial neural networks versus multivariate statistics: An application from economics , 1999 .

[36]  C. Granger,et al.  Modelling Nonlinear Economic Relationships , 1995 .

[37]  Manfred M. Fischer,et al.  A Genetic-Algorithms Based Evolutionary Computational Neural Network for Modelling Spatial Interaction Data , 1998 .

[38]  Terry R. Rakes,et al.  The effect of sample size and variability of data on the comparative performance of artificial neural networks and regression , 1998, Comput. Oper. Res..

[39]  Thomas Riechmann,et al.  Learning in Economics: Analysis and Application of Genetic Algorithms , 2001 .

[40]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[41]  Christian Bayer,et al.  Convergence in West German Regional Unemployment Rates , 2007 .

[42]  Franz-Josef Bade.  Evolution of Regional Employment in Germany: Forecasts 2001 to 2010 , 2006 .

[43]  Manfred M. Fischer,et al.  A genetic-algorithms based evolutionary computational neural network for modelling spatial interaction dataNeural network for modelling spatial interaction data , 1998 .

[44]  Norman R. Swanson,et al.  A Model Selection Approach to Real-Time Macroeconomic Forecasting Using Linear Models and Artificial Neural Networks , 1997, Review of Economics and Statistics.

[45]  Amit Mitra,et al.  Forecasting daily foreign exchange rates using genetically optimized neural networks , 2002 .