《A real-time adaptive trading system using genetic programming》.pdf

Q UANTITATIVE F I N A N C E V O L U M E 1 (2001) 397–413 RE S E A R C H PA P E R I N S T I T U T E O F P H Y S I C S P U B L I S H I N G A real-time adaptive trading system using genetic programming M A H Dempster and C M Jones1 2 Centre for Financial Research , Judge Institute of Management, University of Cambridge, Trumpington Street, Cambridge, CB2 1AG, UK E-mail: mahd@jims.cam.ac.uk and cmj24@cam.ac.uk Received 15 October 2000 Abstract Technical analysis indicators are widely used by traders in financial and commodity markets to predict future price levels and enhance trading profitability. We have previously shown anumber of popular indicator-based trading rules to be loss-making when applied individually in asystematic manner. However, technical traders typically use combinations of abroad range of technical indicators. Moreover, successful traders tend to adapt to market conditions by ‘dropping’ trading rules as soon as they become loss-making or when more profitable rules are found. In this paper we try to emulate such traders by developing atrading system consisting of rules based on combinations of different indicators at different frequencies and lags. An initial portfolio of such rules is selected by agenetic algorithm applied to number of indicators calculated on aset of US Dollar/British Pound spot foreign exchange tick dat afrom 1994 to 1997 aggregated to various intraday frequencies. The genetic algorithm is subsequently used at regular intervals on out-of-sample dat ato provide new rules and afeedback system is utilized to rebalance the rule portfolio, thus creating two levels of adaptivity. Despite the individual indicators being generally loss-making over the dat