This dissertation addresses the statistical aspects of neural networks and their usability for solving problems in economics and finance. Neural networks are discussed in a framework of modelling which is generally accepted in econometrics. Within this framework a neural network is regarded as a statistical technique that implements a model-free regression strategy. Model-free regression seems particularly useful in situations where economic theory cannot provide sensible model specifications. Neural networks are applied in three case studies: modelling house prices; predicting the production of new mortgage loans; predicting the foreign exchange rates. From these case studies is concluded that neural networks are a valuable addition to the econometrician's toolbox, but that they are no panacea.
|Qualification||Doctor of Philosophy|
|Award date||9 Feb 1996|
|Place of Publication||Tilburg|
|Publication status||Published - 1996|