Improved the Least Square Regression Line Method to Develop A Predict Method for Discriminate the Trend of Stock Price in Future

Abstract

The paper described the least square regression line method has been improved as a novel method for tendency discrimination on future stock price. A new method is established, which is obtained from one dataset of known strain variables. The result is been calculated from 10 strain variables consist of one dataset through a few unique managing approaches to calculate out four different tendencies, and encode them. Those codes are added into the least square regression line method by the application software of MATLAB to develop a diagnostic method, which can predict the tendency by the text and graphics. The new method predicts trends more clearly and easily than the least square regression line method. In this paper, firstly establish any of the four standard graphics that can be generated from known data. Finally, it is verified by historical data and the graphics are compared. The result is consistent with both text recognition and graphics trend. The new novel method of the least square regression line was as accurate and alike as we had expected. So that it is enough to prove that it is not only easy to understand but also easy to operate for discriminating the trend of stock price in future.