Title :
A neural network model to exploit the econometric properties of Austrian IPOs
Author :
Haefke, Christian ; Helmenstein, Christian
Author_Institution :
Dept. of Econ, Inst. for Adv. Studies, Vienna, Austria
Abstract :
Applies cointegration and Granger (1969) causality analyses to specify linear and neural network error-correction models for IPOXATX (Initial Public Offerings indeX for the Austrian Traded indeX). We use the significant relationship between IPOXATX and the Austrian stock market index ATX to forecast IPOXATX . For prediction purposes, we apply augmented feedforward neural networks whose architecture is determined by sequential network construction with the Schwartz (1978) 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
Keywords :
economic cybernetics; error correction; feedforward neural nets; financial data processing; forecasting theory; investment; neural net architecture; stock markets; Austrian Traded Index; Granger-causality analyses; IPOXATX; Initial Public Offerings Index; Schwartz information criterion; augmented feedforward neural network architecture; buy-and-hold trading strategies; cointegration; econometric properties; forecasting; linear error-correction models; moving-average trading strategies; neural network error-correction models; prediction risk estimation; return on investment; sequential network construction; stock market index; trading schemes; Contracts; Econometrics; Economic forecasting; Feedforward neural networks; Fluctuations; Multi-layer neural network; Neural networks; Predictive models; Profitability; Stock markets;
Conference_Titel :
Computational Intelligence for Financial Engineering, 1995.,Proceedings of the IEEE/IAFE 1995
Conference_Location :
New York, NY
Print_ISBN :
0-7803-2145-6
DOI :
10.1109/CIFER.1995.495265
