A multi-granularity heterogeneous combination approach to crude oil price forecasting

Crude oil price forecasting has attracted much attention due to its significance on commodities market as well as nonlinear complexity in prediction task. Combining forecasts in different granular spaces, we propose a multi-granularity heterogeneous combination approach to enhance forecasting accuracy in the study. Firstly, we introduce various feature selection techniques including filter, wrapper and embedded methods, to identify key factors that affect crude oil price and construct different granular spaces. Secondly, distinct feature subsets distinguished by different feature selection methods are incorporated to generate individual forecasts using three popular forecasting models including Linear regression (LR), Artificial neural network (ANN) and Support vector machine (SVR). Finally, the final forecasts are obtained by combining the forecasts from individual forecasting model in each granular space and the optimal weighting vector is achieved by artificial bee colony (ABC) techniques. The experimental results demonstrate that the proposed multi-granularity heterogeneous combination approach based on ABC can outperform not only individual competitive benchmarks but also single-granularity heterogeneous and multi-granularity homogenous approaches.