Time Series Forecasting Model Based on Discrete Grey LS-SVM

Abstract

The advantages and disadvantages of discrete GM(1,1) model and least squares support vector machine are analyzed respectively, this article proposes a new time series forecasting model of discrete grey least squares support vector machine. The new model adopts structural risk minimization principle, at the same time develops the advantages of accumulation generation in the grey forecasting method, weakens the effect of stochastic-disturbing factors in original sequence, and avoids the theoretical defects existing in the grey forecasting model. The simulation results show that the forecasting model is effective and reliable, and consolidates the advantage of the discrete GM(1,1) model and least squares support vector machine. It offers a new way to improve the time series forecasting accuracy. Index Terms—Time series prediction, Least square support vector machines algorithm, Grey system, Small samples, Discrete GM(1,1) model, Discrete grey least squares support vector machine .