The prediction of a stock market direction may serve as an earlyrecommendation system for short-term investors and as an early financialdistress warning system for long-term shareholders. Many stock predictionstudies focus on using macroeconomic indicators, such as CPI and GDP, to trainthe prediction model. However, daily data of the macroeconomic indicators arealmost impossible to obtain. Thus, those methods are difficult to be employedin practice. In this paper, we propose a method that directly uses prices datato predict market index direction and stock price direction. An extensiveempirical study of the proposed method is presented on the Korean CompositeStock Price Index (KOSPI) and Hang Seng Index (HSI), as well as the individualconstituents included in the indices. The experimental results show notablyhigh hit ratios in predicting the movements of the individual constituents inthe KOSPI and HIS.
展开▼