The main approach in financial forecasting is to identify trends at an early stage in order to maintain an investment strategy until evidence indicates that the trend has reversed. Predictability of security from past real-world data using two of the simplest and most popular trading rules, namely moving average and trading range break-out rules, were first investigated in [3] on the Dow Jones Index. Other techniques used include regression methods and the ARIMA models [7], but these models fail to give satisfactory forecast for some series because of their linear structures and some other inherent limitations [8]. Although there are also ARCH/GARCH models [9] to deal with the nonconstant variance, these models also fail to give satisfactory forecast for some series [8] (please refer to [10]–[12] for a modern guide to the statistical approach to technical financial forecasting). Increasingly applications of artificial intelligence (AI) techniques, mainly artificial neural networks, have been applied to technical financial forecasting [13]–[15] as they have the ability to learn complex nonlinear mapping and self-adaptation for different statistical distributions (please refer to [16] for a review and evaluation of neural networks in technical financial forecasting). An investigation on the nonlinear predictability of security returns from past real-world returns using single layer feed-forward neural network and moving average rules was presented in [17] on the Dow Jones Index. The results showed that evidence of nonlinear predictability in stock market returns can be found by using the past buy and sell signals of the moving average rules. Application of AI techniques in financial forecasting is not restricted only to the technical analysis approach, but has also been applied to the fundamental approach. For example, in the work of [18], a genetic algorithm based fuzzy neural network is trained with additional political, financial, economic factors etc. to formulate trading decisions. A number of research investigations have been published on the application of AI techniques in the technical analysis approach of forecasting stock price, but only a few presented quantitative results on trading performance using real world stock market data [19]–[24]. Saad et al. [21] performed analysis of predictability based on a history of closing price of a number of high volatility stocks and consumer stocks using time delay, recurrent and probabilistic neural networks. Leigh et al. [22] used neuralnetworks and genetic algorithm to perform pattern recognition of the bull flag pattern and to learn the trading rules from price and volume of the NYSE Composite Index. Results showed that the forecasting method yielded statistically significant returns that are better than the overall average 20-day horizon price increase. Moody et al. [23], [25] used recurrent reinforcement learning without forecasting to train a trading system to trade using past prices of S&P500 stock index while accounting for the effects of transaction costs (please refer to [26] for details on reinforcement learning). Chen et al. [24] used a probabilistic neural network (PNN) to forecast the direction of price moment of the Taiwan Stock Index and presented two PNN-guided investment strategies to translate the predicted direction to trading signals. Field and Singh [20] used Pareto evolutionary neural network (Pareto-ENN) to forecast 37 different international stock indexes.
The main approach in financial forecasting is to identify trends at an early stage in order to maintain an investment strategy until evidence indicates that the trend has reversed. Predictability of security from past real-world data using two of the simplest and most popular trading rules, namely moving average and trading range break-out rules, were first investigated in [3] on the Dow Jones Index. Other techniques used include regression methods and the ARIMA models [7], but these models fail to give satisfactory forecast for some series because of their linear structures and some other inherent limitations [8]. Although there are also ARCH/GARCH models [9] to deal with the nonconstant variance, these models also fail to give satisfactory forecast for some series [8] (please refer to [10]–[12] for a modern guide to the statistical approach to technical financial forecasting). Increasingly applications of artificial intelligence (AI) techniques, mainly artificial neural networks, have been applied to technical financial forecasting [13]–[15] as they have the ability to learn complex nonlinear mapping and self-adaptation for different statistical distributions (please refer to [16] for a review and evaluation of neural networks in technical financial forecasting). An investigation on the nonlinear predictability of security returns from past real-world returns using single layer feed-forward neural network and moving average rules was presented in [17] on the Dow Jones Index. The results showed that evidence of nonlinear predictability in stock market returns can be found by using the past buy and sell signals of the moving average rules. Application of AI techniques in financial forecasting is not restricted only to the technical analysis approach, but has also been applied to the fundamental approach. For example, in the work of [18], a genetic algorithm based fuzzy neural network is trained with additional political, financial, economic factors etc. to formulate trading decisions. A number of research investigations have been published on the application of AI techniques in the technical analysis approach of forecasting stock price, but only a few presented quantitative results on trading performance using real world stock market data [19]–[24]. Saad et al. [21] performed analysis of predictability based on a history of closing price of a number of high volatility stocks and consumer stocks using time delay, recurrent and probabilistic neural networks. Leigh et al. [22] used neuralnetworks and genetic algorithm to perform pattern recognition of the bull flag pattern and to learn the trading rules from price and volume of the NYSE Composite Index. Results showed that the forecasting method yielded statistically significant returns that are better than the overall average 20-day horizon price increase. Moody et al. [23], [25] used recurrent reinforcement learning without forecasting to train a trading system to trade using past prices of S&P500 stock index while accounting for the effects of transaction costs (please refer to [26] for details on reinforcement learning). Chen et al. [24] used a probabilistic neural network (PNN) to forecast the direction of price moment of the Taiwan Stock Index and presented two PNN-guided investment strategies to translate the predicted direction to trading signals. Field and Singh [20] used Pareto evolutionary neural network (Pareto-ENN) to forecast 37 different international stock indexes.
การแปล กรุณารอสักครู่..
