Neural network model to exploit the econometric properties of Austrian IPOs

Christian Haefke; Christian Helmenstein

Neural network model to exploit the econometric properties of Austrian IPOs

Economics

Research output: Contribution to conference › Paper › peer-review

Abstract

In this paper we apply cointegration and Granger-causality analyses to specify linear and neural network error-correction models for an Austrian Initial Public Offerings IndeX (IPOX_ATX). We use the significant relationship between the IPOX_ATX and the Austrian Stock Market Index ATX to forecast the IPOX_ATX. For prediction purposes we apply augmented feedforward neural networks whose architecture is determined by Sequential Network Construction with the Schwartz Information Criterion as an estimator for the prediction risk. The results suggest that trading schemes based on the forecasts significantly increase an investor's return as compared to Buy and Hold or simple Moving Average trading strategies.

Original language	English (US)
Pages	128-135
Number of pages	8
State	Published - 1995
Event	Proceedings of the IEEE/IAFE 1995 Computational Intelligence for Financial Engineering (CIFEr) - New York, NY, USA Duration: Apr 9 1995 → Apr 11 1995

Other

Other	Proceedings of the IEEE/IAFE 1995 Computational Intelligence for Financial Engineering (CIFEr)
City	New York, NY, USA
Period	4/9/95 → 4/11/95

ASJC Scopus subject areas

General Computer Science
Economics, Econometrics and Finance(all)
General Engineering

Cite this

@conference{2971be2774a245c2b2d91010a2c8c149,

title = "Neural network model to exploit the econometric properties of Austrian IPOs",

abstract = "In this paper we apply cointegration and Granger-causality analyses to specify linear and neural network error-correction models for an Austrian Initial Public Offerings IndeX (IPOXATX). We use the significant relationship between the IPOXATX and the Austrian Stock Market Index ATX to forecast the IPOXATX. For prediction purposes we apply augmented feedforward neural networks whose architecture is determined by Sequential Network Construction with the Schwartz Information Criterion as an estimator for the prediction risk. The results suggest that trading schemes based on the forecasts significantly increase an investor's return as compared to Buy and Hold or simple Moving Average trading strategies.",

author = "Christian Haefke and Christian Helmenstein",

year = "1995",

language = "English (US)",

pages = "128--135",

note = "Proceedings of the IEEE/IAFE 1995 Computational Intelligence for Financial Engineering (CIFEr) ; Conference date: 09-04-1995 Through 11-04-1995",

}

TY - CONF

T1 - Neural network model to exploit the econometric properties of Austrian IPOs

AU - Haefke, Christian

AU - Helmenstein, Christian

PY - 1995

Y1 - 1995

N2 - In this paper we apply cointegration and Granger-causality analyses to specify linear and neural network error-correction models for an Austrian Initial Public Offerings IndeX (IPOXATX). We use the significant relationship between the IPOXATX and the Austrian Stock Market Index ATX to forecast the IPOXATX. For prediction purposes we apply augmented feedforward neural networks whose architecture is determined by Sequential Network Construction with the Schwartz Information Criterion as an estimator for the prediction risk. The results suggest that trading schemes based on the forecasts significantly increase an investor's return as compared to Buy and Hold or simple Moving Average trading strategies.

AB - In this paper we apply cointegration and Granger-causality analyses to specify linear and neural network error-correction models for an Austrian Initial Public Offerings IndeX (IPOXATX). We use the significant relationship between the IPOXATX and the Austrian Stock Market Index ATX to forecast the IPOXATX. For prediction purposes we apply augmented feedforward neural networks whose architecture is determined by Sequential Network Construction with the Schwartz Information Criterion as an estimator for the prediction risk. The results suggest that trading schemes based on the forecasts significantly increase an investor's return as compared to Buy and Hold or simple Moving Average trading strategies.

UR - http://www.scopus.com/inward/record.url?scp=0029493416&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029493416&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029493416

SP - 128

EP - 135

T2 - Proceedings of the IEEE/IAFE 1995 Computational Intelligence for Financial Engineering (CIFEr)

Y2 - 9 April 1995 through 11 April 1995

ER -

Neural network model to exploit the econometric properties of Austrian IPOs

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this