Study on Stock Trading and Portfolio Optimization using Genetic Network Programming

Research on stock price prediction and trading model using evolutionary computation has been done in recent years. As we know, prediction in the stock market is quite difficult for a number of reasons. First, the ultimate goal of our research is not to minimize the prediction error, but to maximize the profits. Second, the weak relationships among variables tend to be nonlinear, and they may hold only in limited areas of the search space. Finally, since the stock market data are given in an event-driven way, they are highly influenced by the indeterminate dealing. Generally speaking, there are two kinds of methods for predicting stock prices and determining the timing of buying or selling stocks: one is fundamental analysis which analyzes stock prices using the financial statement of each company, the economic trend and movements of the exchange rate; the other is technical analysis which analyzes numerically the past movement of stock prices. The proposed method belongs to technical analysis since it determines the stock trading actions based on the technical indices such as Relative Strength Index, MACD, Golden/Dead Cross and so on. The most recent literature in the related fields exposed Portfolio Optimization, Investment Strategy Determination, and Market Risk Analysis as three major trends in the utilization of evolutionary algorithms. Our research focuses on the problem of Investment Strategy Determination and Portfolio Optimization through the use of Genetic Network Programming (GNP) with reinforcement learning technique. The objective of this work is to provide an unique technique of decision-making for investors. First, it presents a stock trading model based on GNP and Sarsa learning by the use of Importance Index (IMX) and candlestick charts. Appropriate trading actions can be determined with the proposed model depending on the situation. Second, it extends an application of GNP with control node (GNPcn) to the portfolio optimization problem. Third, it proposes a new method name Genetic Relation Algorithm (GRA) and applies