Developing Multi-Time Frame Trading Rules with a Trend Following Strategy, using GA
Developing Multi-Time Frame Trading Rules with a Trend Following Strategy, using GA, Proc Genetic and Evolutionary Computation Conf. - GECCO, madrid, Spain, Vol. 1, pp. 765 - 766, July, 2015.
Digital Object Identifier:
This paper describes a novel way to develop trading rules with a trend following philosophy, combining several time-frames which average the Rate of Return of the several components and decrease the Maximum Drawdown. This represents strategy diversification and is an effective way to reduce risk. The resulting trading systems have the interesting characteristic of producing an output that is not binary in terms of market position, giving a varying degree of confidence in the future direction of the market. Tests performed with a sliding window on American stock index S&P500, produced annualized Rates of Return in excess of 10% in some configurations.