ناهید دانا

In this study we focus on developing a stock trend prediction model based on a modified version of support vector machine, named volume weighted support vector machine, along with a hybrid feature selection method named FSSFS method. In order to evaluate the prediction accuracy of this model we compare the VW-SVM classifier with plain support vector machine along with three commonly used feature selection methods including Information gain, Symmetrical uncertainty and correlation-based feature selection, via paired t-test. As the model input, we use several technical indicators and statistical measures, calculated for 10 stocks. The results show that the VW-SVM, combined with the hybrid feature selection method, significantly outperforms plain SVM model to the problem of stock trend prediction. In addition our experimental result show that VW-SVM combined with F-SSFS has the highest level of accuracies and generalization performance in comparison with the other three feature selection methods. With these results, we claim that VW-SVM combined with F-SSFS can serve as a promising addition to the existing stock trend prediction.

In this study, a prediction model based on support vector machines (SVM) improved by introducing a volume weighted penalty function to the model was introduced to increase the accuracy of forecasting short term trends on the stock market to develop the optimal trading strategy. Along with VW-SVM classifier, a hybrid feature selection method was used that consisted of F-score as the filter part and supported Sequential forward selection as the wrapper part, to select the optimal feature subset. In order to verify the capability of the proposed model in successfully predicting short term trends, a trading strategy was developed. The model input included several technical indicators and statistical measures that were calculated for chosen 10 stocks from Tehran Stock Exchange. The results show that the VW-SVM, combined with the hybrid feature selection method, significantly increases the profitability of the proposed strategy compared to rival strategies, in terms of both overall rate of return and the maximum draw down during trading period.