Stock Returns Prediction Using Manifold Wavelet Kernel

作者：Lingbing Tang, Huanye Sheng, Lingxiao Tang · 年份：2009 · DOI：10.1109/ecbi.2009.67 · 被引用次数：2 · 研究领域：Neural Networks and Applications、Image and Signal Denoising Methods、Advanced Image Fusion Techniques

An admissible manifold wavelet kernel is proposed to construct manifold wavelet support vector machine (MWSVM) for forecasting stock returns. The manifold wavelet kernel is obtained by incorporating manifold theory into wavelet technique in support vector machine (SVM). Since manifold wavelet function can yield features that describe of the stock time series both at various locations and at varying time granularities, the MWSVM can approximate arbitrary nonlinear functions and forecast stock returns accurately. The applicability and validity of MWSVM for stock returns forecast is confirmed through experiments on real-world stock data.