The development of Regional employment in Germany: Results from Neural Network Experiments (by Roberto Patuelli, Aura Reggiani, Peter Nijkamp) - ABSTRACT: This paper offers an overview of experimental results, based on neural networks (NNs) used to forecast regional employment variations in Germany. NNs are statistical optimization tools, whose main characteristics are non-linear data processing and the ability to find functional relationships within the data. We present the results – for a set of NN models – based on regional data concerning full-time employment in Germany. The database used in our experiments consists of two panels of 326 and 113 NUTS 3 districts, which represent West and East Germany, respectively. In order to forecast employment growth rates for the years 2004, 2005, and 2006, NN models – also embedding shift-share analysis components – were developed and evaluated for West and East Germany. The paper concludes with theoretical, methodological and empirical observations in the light of future research developments.