Modelling and trading the London, New York and Frankfurt stock exchanges with a new gene expression programming trader tool

摘要

The scope of this manuscript is to present a new short‐term financial forecasting and trading tool:rnthe Gene Expression Programming (GEP) Trader Tool. It is based on the gene expression programmingrnalgorithm. This algorithm is based on a genetic programming approach, and providesrnsupreme statistical and trading performance when used for modelling and trading financial timernseries. The GEP Trader Tool is offered through a user‐friendly standalone Java interface. Thisrnpaper applies the GEP Trader Tool to the task of forecasting and trading the future contractsrnof FTSE100, DAX30 and S&P500 daily closing prices from 2000 to 2015. It is the first time thatrngene expression programming has been used in such massive datasets. The model's performancernis benchmarked against linear and nonlinear models such as random walk model, a movingaveragernconvergence divergence model, an autoregressive moving average model, a genetic programmingrnalgorithm, a multilayer perceptron neural network, a recurrent neural network a higherrnorder neural network. To gauge the accuracy of all models, both statistical and trading performancesrnare measured. Experimental results indicate that the proposed approach outperformsrnall the others in the in‐sample and out‐of‐sample periods by producing superior empirical results.rnFurthermore, the trading performances are improved further when trading strategies are imposedrnon each of the models.