The Equity Premium Puzzle: An Artificial Neural Network Approach

23 Pages Posted: 8 Aug 2008 Last revised: 28 Aug 2014

Shee Q. Wong

Labovitz School of Business

Nik R. Hassan

University of Minnesota - Duluth

Ehsan H. Feroz

Accounting Area, University of Washington-Milgard School of Business, Tacoma, USA; Vernon Zimmerman Center, University of Illinois Urbana-Champaign; U.S. Government Accountability Office; Department of Accounting, University of Minnesota, Duluth

Date Written: August 8, 2008

Abstract

This paper presents evidence suggesting that artificial neural networks approach (ANNs) outperform traditional statistical methods and can forecast equity premiums reasonably well. The study replicates out-of-sample estimates of regression using ANN with economic fundamentals as inputs. The dividend yield variable was found to produce the best out-of-sample forecasts for equity premium. This result is useful for capital asset pricing model and in asset allocation decisions.

Keywords: Equity premium, Forecasting, CAPM, Neural networks

JEL Classification: C45, G1, G2, G3

Suggested Citation

Wong, Shee Q. and Hassan, Nik R. and Feroz, Ehsan H., The Equity Premium Puzzle: An Artificial Neural Network Approach (August 8, 2008). Review of Accounting and Finance, Vol. 6, No. 2, pp. 150-161, 2007 . Available at SSRN: https://ssrn.com/abstract=1211962

Shee Q. Wong

Labovitz School of Business ( email )

412 Library Drive
Duluth, MN 55812
United States

Nik R. Hassan

University of Minnesota - Duluth ( email )

1049 University Drive
Duluth, MN 55812
United States

Ehsan H. Feroz (Contact Author)

Accounting Area, University of Washington-Milgard School of Business, Tacoma, USA ( email )

1900 Commerce Street, Campus Box 358420
Tacoma, WA 98402-3100
United States
(253) 692 4728 (Phone)
253 692 4523 (Fax)

HOME PAGE: http://www.tacoma.washington.edu/business

Vernon Zimmerman Center, University of Illinois Urbana-Champaign ( email )

515 East Gregory Drive# 2307
Champaign, IL 61820
United States

U.S. Government Accountability Office ( email )

441 G Street NW
Washington, DC 20548-0001
United States

Department of Accounting, University of Minnesota, Duluth ( email )

10 University Drive
137 SBE
Duluth, MN 55812
United States
218-726-6988 (Phone)
218-726-8510 (Fax)

Paper statistics

Downloads
178
Rank
138,080
Abstract Views
1,502