Stock Prices are considered to be very dynamic and susceptible to quick changes because of the underlying nature of the financial domain, and in part because of the interchange between known parameters and unknown factors. Of late, several researchers have used Piecewise Linear Representation (PLR) to predict the stock market pricing. However, some improvements are needed to avoid the appropriate threshold of the trading decision, choosing the input index as well as improving the overall performance. In this paper, several techniques of data mining are discussed and applied for predicting price movement. For example, a new technique named Local Saturation Method (LSM) has been used to find the PLR; the weighted moving average has been applied to find recent price moves; the Shannon entropy has been used for measuring the data set complexity or nature; an intelligent system is used to select the new and important technical indexes; and finally, Ensemble Neural Networks (ENN) have been used in order to improve the overall performance. Our method has been tested by thirty problems, including up trade, down trade and steady state features. By applying all those techniques, the proposed algorithm shows good predictions with a hit rate of about 60 percent.
展开▼
