Neural networks in the capital markets: An application to index forecasting

Christian Hæfke, Christian Helmenstein

Research output: Contribution to journalArticlepeer-review


In this article we construct an Index of Austrian Initial Public Offerings (IPOX) which is isomorph to the Austrian Traded Index (ATX). Conjecturing that the ATX qualifies as an explaining variable for the IPOX, we investigate the time trend properties of and the comovement between the two indices. We use the relationship to construct a neural network and a linear error-correction forecasting model for the IPOX and base a trading scheme on each forecast. The results suggest that trading based on the forecasts significantly increases an investor's return as compared to Buy and Hold or simple Moving Average trading strategies.

Original languageEnglish (US)
Pages (from-to)37-50
Number of pages14
JournalComputational Economics
Issue number1
StatePublished - 1996

ASJC Scopus subject areas

  • Economics, Econometrics and Finance (miscellaneous)
  • Computer Science Applications


Dive into the research topics of 'Neural networks in the capital markets: An application to index forecasting'. Together they form a unique fingerprint.

Cite this