Discovering Financial Patterns in the Foreign Exchange Markets

Chueh-Yung Tsao and Shu-Heng Chen

No 203, Computing in Economics and Finance 2004 from Society for Computational Economics

Abstract: Motivated from the charting analysis in the financial industry, Chen and He (2003) are the first to use self-organizing maps to search for and identify price patterns. Such a model is referred to as the trajectory-domain model (TDM). Chen and Tsao (2003) apply the TDMs to three American stock indices, including the Dow Jones, Nasdaq, and S&P 500. It is found that there is some evidence to support the relevance of the TDM to informative pattern discovery. Some patterns discovered by the TDMs can in effect transmit signals of abnormal returns. In this study, we examine a number of interesting questions for the application of the TDM. First, while the TDM seems to be successful in the stock markets, we ask whether the TDM can still discover informative patterns in the foreign exchange markets. In particular, we consider four foreign exchange rates, including TWD/USD, GBP/USD, JPY/USD, and HKD/USD. Second, Neely and Weller (1999) apply the trading rules discovered from DEM/USD to the European Monetary System and conclude that the rules perform well for some of the currencies. This finding seems to suggest that the profitable trading rules discovered from one market could be transferred to one another market. The question we are interested here is to see if the similar results exist when the trading rule is based on the geometric patterns, in particular, the patterns discovered by TDM.

Keywords: Trajectory-Domain Model; Self-Organizing Maps; Charting Analysis; Exchange Rates (search for similar items in EconPapers)
JEL-codes: C45 C51 G14 (search for similar items in EconPapers)
Date: 2004-08-11
References: Add references at CitEc
Citations:

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: https://EconPapers.repec.org/RePEc:sce:scecf4:203

Access Statistics for this paper

More papers in Computing in Economics and Finance 2004 from Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Christopher F. Baum ().