
handle: 10419/68650
In most of the empirical research on capital markets, stock market indexes are used as proxies for the aggregate market development. In previous work we found that a particular market segment might be less efficient than the whole market and hence easier to forecast. In this paper we extend the focus of this investigation by taking a comprehensive look at the Vienna Stock Exchange. We use feedforward networks and linear models to forecast the all share index WBI as well as various subindexes covering the highly liquid, semi-liquid, and initial public offering (IPO) market segment. In order to shed some light on network construction principles, we compare different models as selected by hold-out crossvalidation (HCV), Akaike's information criterion (AIC), and Schwartz' information criterion (SIC). The forecasts are subsequently evaluated on the basis of hypothetical trading in the out-of-sample period.
In der empirischen Kapitalmarktforschung werden Aktienindizes oft als Maß für die aggregierte Marktentwicklung herangezogen. Frühere Arbeiten ergaben, daß spezifische Marktsegmente nicht so effizient wie der Gesamtmarkt und daher leichter zu prognostizieren sind. Hier wenden wir diesen Ansatz auf Wiener Aktienkursdaten an. Wir verwenden lineare und feedforward Netzwerke Modelle, um den Gesamtmarktindex WBI sowie verschiedene Subindizes für das hochliquide, semi-liquide und Erstemissionsmarktsegment zu prognostizieren. Um die Transparenz bei der Architekturselektion für neuronale Netzwerke zu erhöhen, vergleichen wir Modelle auf der Basis von Hold-out Kreuzvalidierung (HCV), Akaike Informationskriterium (AIC) und Schwartz Informationskriterium (SIC). Die Güte der Prognosen wird anhand einer Tradingsimulation für die out-of-sample Periode bestimmt.
ddc:330, neural network architecture selection, Neural Network Architecture Selection, Information Criteria, Stock Market Indexes, Trading Strategy, Börsenkurs, C52, stock market indexes, Prognoseverfahren, C53, information criteria, trading strategy, C43, Finanzmarkt, Theorie, C45, Neuronale Netze, jel: jel:C52, jel: jel:C53, jel: jel:C45, jel: jel:C43
ddc:330, neural network architecture selection, Neural Network Architecture Selection, Information Criteria, Stock Market Indexes, Trading Strategy, Börsenkurs, C52, stock market indexes, Prognoseverfahren, C53, information criteria, trading strategy, C43, Finanzmarkt, Theorie, C45, Neuronale Netze, jel: jel:C52, jel: jel:C53, jel: jel:C45, jel: jel:C43
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
