Predicting Recession Using the Yield Curve: An Artificial Intelligence and Econometric Comparison

Mohamad Shaaf
Additional contact information
Mohamad Shaaf: University of Central Oklahoma

Eastern Economic Journal, 2000, vol. 26, issue 2, 171-190

Abstract: Normally the yield curve has an upward slope and is slightly convex. There are times when the curve becomes flat or slopes downward, which signals an approaching economic slowdown soon. Although simple, the yield curve has often been more successful at predicting recession than larger and/or more complex econometric models. Using an artificial intelligence methodology called "neural networks" and quarterly data from 1959 to 1997, the purpose of this study was to use the yield curve for forecasting recessions. The results confirm earlier findings that used econometric modelling, and suggest that the yield curve is a very useful tool for the prediction of recession. Furthermore, the results of the out-of-sample simulation imply that the forecast of the artificial intelligence method is more accurate than that of the traditional econometric model.

Keywords: Econometrics; Neural Networks; Neural (search for similar items in EconPapers)
JEL-codes: C45 C53 E37 (search for similar items in EconPapers)
Date: 2000
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://web.holycross.edu/RePEc/eej/Archive/Volume26/V26N2P171_190.pdf (application/pdf)

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:eej:eeconj:v:26:y:2000:i:2:p:171-190

Access Statistics for this article

Eastern Economic Journal is currently edited by Cynthia A. Bansak, St. Lawrence University and Allan A. Zebedee, Clarkson University

More articles in Eastern Economic Journal from Eastern Economic Association Contact information at EDIRC.
Bibliographic data for series maintained by Victor Matheson, College of the Holy Cross ().