Neural Networks as tools for increasing the forecast and control of complex economic systems. Economics & Complexity - 1999\Vol2 N2 Spec. NEU 99-a
AbstractThe 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.
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoPaper provided by EconWPA in its series Macroeconomics with number 0501012.
Length: 10 pages
Date of creation: 07 Jan 2005
Date of revision:
Note: Type of Document - pdf; pages: 10
Contact details of provider:
Web page: http://188.8.131.52
Neural Network; Public Finance; Control of Economics; Macroeconomics;
Find related papers by JEL classification:
- E - Macroeconomics and Monetary Economics
This paper has been announced in the following NEP Reports:
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Haefke, Christian & Helmenstein, Christian, 1996. "Neural Networks in the Capital Markets: An Application to Index Forecasting," Computational Economics, Society for Computational Economics, vol. 9(1), pages 37-50, February.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (EconWPA).
If references are entirely missing, you can add them using this form.