On the application of a genetic algorithm to finding parameters of the trading system

• Języki publikacji: EN

Abstrakty

EN

In this paper the process of developing trading systems (transaction systems) is considered. For convenience, we define trading system as a specialized software or algorithm which analyses historical time series data representing quotations of some financial instrument in order to discover repeating patterns (regularities) in their behavior and which generates entry and exit signals for the trader when these patterns are re-discovered in actual data. The signals generated by the system may represent simple decisions, (e.g. "buy now at any price") or they may involve some trading limits, (e.g. the activation limit or stop-loss limit). There are several types of trading systems. Some of them rely on forecasting the future value of a traded financial instrument using tools provided by the prediction theory. Others identify and follow trends (momentum-based systems) or try to detect a trend change beforehand by using oscillators or employing supervised learning algorithms to identify characteristic patterns of market behavior like "double bottom" or "head-and-shoulders" reversal formations well-known from technical analysis. (fragment of text)

Słowa kluczowe

EN

Genetic algorithms; Transaction systems; Internet application

PL

Algorytmy genetyczne; Systemy transakcyjne; Aplikacje internetowe

• Czasopismo: Prace Naukowe / Akademia Ekonomiczna w Katowicach
• Rocznik: 2008
• Tom: Metody matematyczne, ekonometryczne i komputerowe w finansach i ubezpieczeniach 2006
• Strony: 271--280

Twórcy

Bibliografia

• Davis L.: Handbook of Genetic Algorithms. Van Nostrand, New York 1991
• Goldberg D.E.: Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley 1989
• Holland J.H.: Adaptation in natural and artificial systems. Ann Arbor: Michigan University Press 1975
• Murphy J.J.: Technical Analysis of the Financial Markets. New York Institute of Finance 1999