Grey relational grade in local support vector regression for financial time series prediction

► Support vector regression (SVR) has often been applied in the prediction of time series. ► We introduce local grey SVR (LG-SVR) for financial time series forecasting. ► Grey relational grade is regarded as weighting function with LG-SVR. ► Leave-one-out errors and pattern search method are adopted for model selection. ► Experiments demonstrate LG-SVR can speed up computing speed and improve prediction accuracy.