Automatic Extraction of Derivative Market Prices from Webpages using a Software Agent

Patrick Bartels () and Michael H. Breitner ()
Additional contact information
Patrick Bartels: Institut für Wirtschaftsinformatik, Universität Hannover, http://www.iwi.uni-hannover.de/mitarbeiter/pb.html

No 4, IWI Discussion Paper Series from Institut für Wirtschaftsinformatik, Universität Hannover

Abstract: Some current research of derivative pricing is dedicated to artificial neural networks to generate market prices (see Breitner (2000 and 2001)) instead of analytical prices developed by Black, Scholes and Merton (1973) or Cox, Ross and Rubinstein (1979). Needed data are usually taken from commercial finance databases. This paper presents the software agent PISA[1] extracting quotes from webpages to generate cost free quote databases. Such databases provide time series for the training of neural networks. Extrapolating series with neural networks enables all kinds of forecasting. Interpolating data obtained enables, e. g., a comparison of derivative prices from different issuers and a synthesis of market price functions. This paper presents a comparison of selected programming languages to find the most suitable for the given tasks. The components of PISA are described in detail. The paper closes with examples for the extraction process.

Keywords: Software agent; market prices; derivatives; artificial neural networks (search for similar items in EconPapers)
Date: 2003-05-20
Note: PDF document available via email.

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:ifw:iwidps:iwidps04

Ordering information: This working paper can be ordered from

Access Statistics for this paper

More papers in IWI Discussion Paper Series from Institut für Wirtschaftsinformatik, Universität Hannover
Address: Königsworther Platz 1, D-30167 Hannover
Contact information at EDIRC.
Series data maintained by RePEc-Administrator ().