Investment opportunities forecasting: a genetic programming-based dynamic portfolio trading system under a directional-change framework

Abstract

This paper presents an autonomous effective trading system devoted to the support of decision-making processes in the financial market domain. Genetic programming (GP) has been used effectively as an artificial intelligence technique in the financial field, especially for forecasting tasks in financial markets. In this paper, GP is employed as a means of automatically generating short-term trading rules on financial markets using technical indicators and fundamental parameters. The majority of forecasting tools use a fixed physical timescale, which makes the flow of price fluctuations discontinuous. Therefore, using a fixed physical timescale may expose investors to risks, due to their ignorance of some significant activities. Instead of using fixed timescales for this purpose, the trading rules are generated under a directional-change (DC) event framework.We examine the profitability of the trading systems for the Saudi Stock Exchange, and evaluate the GP forecasting performance under a DC framework through agent-based simulation market index trading. The performance of the forecasting model is compared with a number of benchmark forecasts, namely the buy-and-hold and technical analysis trading strategies. Our numerical results show that the proposed GP model under a DC framework significantly outperforms other traditional models based on fixed physical timescales in terms of portfolio return.