Multiscale rough set data analysis with application to stock performance modeling

Abstract

Multiscale Rough Set Data Analysis (MSRSDA) combines the feature selection and feature extraction ability of RSDA with the multiresolution property of the wavelet transform. RSDA removes the irrelevant (having no impact on prediction performance) and dependent (having no discriminatory power) market variables from the multivariate time series data matrix, thereby improving generalization capability of the forecasting engine (neural network, fuzzy inference system). A wavelet transform is used to decompose the time series into varying scales of resolution so that the underlying temporal structures of the original time series become more tractable; the decomposition is additive in details and approximation. Significance of market variables at various wavelet scales representing detailed short-term history and general long-term history of the time series, is computed using RSDA in wavelet space. Irrelevant and redundant variables at each scale are removed and a forecasting engine is then trained on each of the relevant resolution scales (i.e., those scales where significant events are detected); individual wavelets forecasts are recombined to form the overall forecast. The superior performance of MSRSDA is illustrated through stock performance modeling example. For prediction of S&P500 index, a data matrix of 21 variables has been used. MSRSDA gives 69% accuracy on stock-trend prediction.