Spare parts consumption rolling forecasting model based on grey LSSVM

Considering the limited data of spare parts consumption and the stochastic and uncontrollable of the inducing factors, a new rolling forecasting model of grey least square support vector machine (LSSVM) is proposed through analyzing disadvantages of current spare parts consumption forecasting models. The new model not only develops the advantages of accumulation generation of the grey forecasting method, weakens the effect of stochastic-disturbing factors in original sequence and strengthened the regularity of data, but also uses the quickly solving speed and the excellent characteristics of least square support vector machines for nonlinear relationship and avoids the theoretical defects existing in the grey forecasting model. Through continuous interaction between predictive value and statistical value to update the training samples, the model realizes the rolling forecasts of the spare parts consumption. At last, one example is given to testify the effectiveness of the model.