Selection of technical analysis indicator for optimizing porfolio performance with genetic algorithms

Technical indicators are widely used in stock market forecasting, mostly to trigger the buy/sell rules in the technical analysis. Through some statistical analysis some key values for several indicator parameters are obtained. These values are generally adjusted to provide simple, round numbers, so they become part of easy-to-remember rules. However, it is not clear how changing market conditions affect them. An investor who does not know which technical indicator is used in which conditions and with which values, can experience big losses due to inappropriate rule selection. In this study, the performances of several different ETFs are analyzed using different technical indicators. The indicator parameters are optimized against portfolio performance using genetic algorithms thus, optimum rules are generated with those parameters. During the study, different analyses are implemented according to different market conditions (uptrend or downtrend) with using an ETF or a basket of ETFs for each technical indicator used in the study. Generated rules are tested in different time period and the performance of each rule is calculated. Moreover, new rules are generated with the method of combining different technical indicators in a rule to get higher profits instead of using only one indicator in a rule.