Tunable free parameters C and epsilon-tube in support vector regression for grey prediction model - SVRGM(1,1C,e) approach

摘要

This paper introduces a novel SVRGM(1,1|C,e) prediction model for forecasting economic indexes like stock price indexes or future trading indexes. SVRGM(1,1|C,e) model employ the support vector regression (SVR) learning algorithm to improve the control and environment parameters in grey model GM(1,1) , that is, enhancing generalization capability in the non-periodic short-term prediction. Therefore, this proposed method could reduce the overshooting phenomenon, that often occurred in GM(1,1) model or autoregressive moving-average (ARMA) method, so as to achieve better the prediction accuracy.