Neural Networks as tools for increasing the forecast and control of complex economic systems. Economics & Complexity - 1999\Vol2 N2 Spec. NEU 99-aMacroeconomics from EconWPA Abstract: The idea that NN can be usefully used for a better understanding of economic complex mechanisms is present in the literature. Our interest is to show that this is correct if we use the larger possible amounts of information that data conveys. At this end we will start with the consideration expressed by Mandelbrot that a traditional model could explain the economic behaviour 95% of time, but that in terms of amount the remaining 5% means quite the complete set of phenomena that we want to understand. We need complex models for dealing with this part. For their characteristic of being general approximators NNs seem one of most interesting instrument. This is true both for macroeconomic and for financial data.Often, the economic system is so complex that, to grasp the meaning of the information conveyed by the data, even a general approximator like NN is not enough. Larger information could be obtained using 2 or more instruments in cascade or in parallel. We will concentrate on this topic. We will try to illustrate how the combination of tools is possible. Applications will refer to Italian macroeconomic and financial data. Keywords: Neural Network; Public Finance; Control of Economics; Macroeconomics (search for similar items in EconPapers) Downloads: (external link) Related works: Access Statistics for this paper More papers in Macroeconomics from EconWPA |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
Econpapers is hosted by the
Swedish Business School at Örebro University.