Interest Rate Forecasting with Neural Networks

Jan Täppinen

No 170, Discussion Papers from VATT Institute for Economic Research

Abstract: This paper compares neural networks and linear regression models in interest rate forecasting using US term structure data. The expectations hypothesis gets some extra support from the neural network model as compared to the regression model. A neural network with the whole yield curve spectre from the difference between 1 and 3-month rates to the difference between 5 and 10-year rates predicts changes in interest rates quite well. However, during 1994?1995 the neural networks (as well as the regression) fails in predicting the rising interest rates.

Keywords: Expectations hypothesis, neural networks, forecasting, interest rate, Macroeconomic policy, Talouspolitiikka, Taxation and Social Transfers, Julkisen talouden rahoitus ja tulonsiirrot, C450 - Neural Networks and Related Topics, E430 - Determination of Interest Rates; Term Structure of Interest Rates, (search for similar items in EconPapers)
Date: 1998
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.doria.fi/handle/10024/148103

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:fer:dpaper:170

Ordering information: This working paper can be ordered from

Access Statistics for this paper

More papers in Discussion Papers from VATT Institute for Economic Research Contact information at EDIRC.
Bibliographic data for series maintained by Anita Niskanen ().