Skip to main content

Neural Network vs Linear Models of Stock Returns: An Application to the UK and German Stock Market Indicies

Kanas, Angelos (2001) Neural Network vs Linear Models of Stock Returns: An Application to the UK and German Stock Market Indicies. In: Fuzzy Sets in Management, Economics and Marketing. World Scientific Publishing Co, pp. 181-193. ISBN 978-981-02-4753-9. E-ISBN 978-981-281-089-2. (doi:10.1142/9789812810892_0012) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
http://www.worldscientific.com/worldscibooks/10.11...

Abstract

We compare the out-of-sample performance of monthly returns forecasts for two indices, namely the FAZ and the FT. A linear and a nonlinear artificial neural network (ANN) model are used to generate out-of-sample competing forecasts for monthly returns. We consider two fundamental variables as the explanatory variables in the linear model and the input variables in the ANN model, namely the trading volume and the dividend. The comparison of out-of-sample forecasts is done on the basis of forecast encompassing. The results suggest that the out-of-sample ANN forecasts encompass linear forecasts of both indices. This finding indicates that the inclusion of nonlinear terms in the relation between stock returns and fundamentals is important in out-of-sample forecasti

Item Type: Book section
DOI/Identification number: 10.1142/9789812810892_0012
Subjects: H Social Sciences > HG Finance
Divisions: Faculties > Social Sciences > Kent Business School > Accounting and Finance
Depositing User: Tracey Pemble
Date Deposited: 04 Jun 2014 09:43 UTC
Last Modified: 29 May 2019 12:38 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/41259 (The current URI for this page, for reference purposes)
  • Depositors only (login required):