LAUSR

Abstract This study investigates stock trading signals prediction that is an interesting yet challenging research topic in the area of financial investment, since the stock market is an unstable and complex system affected by many interrelated factors and a small improvement in predictive performance can be profitable. To realize trading signals detection, several methods have been developed, among which artificial intelligence methods have drawn more and more attention by both investors and researchers. In this paper, we propose a complete and efficient method which integrates principal component analysis (PCA) into weighted support vector machine (WSVM) to forecast trading points of the stock (PCA-WSVM). Firstly, we model the stock trading signals prediction as a weighted four-class classification problem. Then, PCA is applied to clean the original data set and re-arrange it to a new data structure. Thirdly, WSVM is used with the transformed data set to forecast the turning points of the stock. Finally, we conduct a series of experiments among PCA-WSVM, WSVM, PCA-ANN and Buy-and-Hold strategy on stocks from two well-known Chinese stock exchange markets, Shanghai and Shenzhen stock exchange markets, to test the performance of our established model. The experiment results reflect that with our proposed model the prediction capability and profitability with different investment strategies are all the best, which indicates PCA-WSVM is effective and can be applied to forecast the stock trading signals in the real-world application.