OEKONOMETRISCHES FORSCHUNGSSEMINAR (M. Deistler, R. Alt, R. Kunst)
Donnerstag, 20. Juni 1996
"Forecasting Stock Market Averages to Enhance Profitable Trading Strategies"
Christian HAEFKE and Christian HELMENSTEIN (IHS)
Abstract:
In this paper we formulate a trading strategy for stocks that exploits the informational difference implied by different stock market index construction principles. In order to gain a competitive advantage over other market participants, we forecast the indexes one day ahead and subsequently generate buy and sell signals through the trading rule. To illustrate how the system works, we apply it to select stocks from those constituting the ATX index sample.
The forecasting of the indexes is done applying standard financial econometric techniques and feedforward neural networks. Drawing upon various model selection criteria, such as AIC, HQ and SIC, we discuss their potential for rendering parsimonious neural network architectures.
Keywords: Artificial Neural Networks, Model Selection, Stock Market Indexes, Trading Systems.
Ort: HS II Zeit: 9.00 Uhr c. t. =========================================================================