Share Price Prediction Using Wavelet Transform and Ant Colony Algorithm for Parameters Optimization in SVM

In this paper, an integrated methodology of wavelet transform and ACO-SVM is applied to predicting share price. On the one hand, the instability of the time series could lead to decrease of prediction accuracy, so wavelet transform (WT) is employed as a preprocessor of SVM to eliminate the fluctuant component of original data. On the other hand, two parameters of SVM must be carefully predetermined in establishing an efficient LS-SVM model, in order to solve this problem, the ant colony optimization algorithm (ACO) is used to optimize the parameters of SVM. A practical prediction of Huaneng Guoji show that the integrated methodology of wavelet transform and ACO-SVM can serve as a promising alternative for share price prediction.