基于尺度分析和动态误差修正的油价选择性集成预测方法

A Selective Ensemble Forecasting Approach Based on Multi-Scale Analysis and Dynamic Error Correction to Crude Oil Price

原油价格的波动对于全球经济的发展具有显著性影响,准确地预测原油价格成为能源经济领域的热点研究课题.传统的计量经济学方法及机器学习方法在预测油价时均存在诸多不足,针对原油价格序列高度非线性、非平稳性和时变性等复杂特性,文章提出一种基于多尺度分析方法和动态误差修正的原油价格集成预测方法.首先,基于多尺度分解和机器学习方法,构建了集成预测的多样化基模型生成机制;进一步地,基于多种策略建立动态误差修正模型提升基模型的预测精度.最后,建立了基于多样性的基模型选择性集成策略.针对布伦特原油市场的实证结果表明,相比传统组合预测策略,文章提出的集成预测方法能够有效提高原油价格预测精度,具有较好的预测性能和泛化能力.

Crude oil price fluctuations have a significant impact on the development of the global economy,and accurate forecasting of crude oil prices has become a hot research topic in the field of energy economy.Traditional econometric methods and machine learning methods have many deficiencies in oil price forecasting.Aiming at the complex characteristics of crude oil price series such as highly nonlinear,nonstationary and time-varying,this paper presents an ensemble forecasting method for crude oil prices based on multi-scale decomposition and dynamic error correction.First,on the basis of multi-scale decomposition and machine learning methods,a diversified base model generation mechanism for ensemble forecasting is constructed.Further,a dynamic error correction model is established based on multiple strategies to improve the forecasting accuracy of the base models.Finally,a diversity-based selective ensemble strategy for base models is established.The empirical results for the Brent crude oil market demonstrate that the ensemble forecasting method proposed in this paper can effectively improve the forecasting accuracy of crude oil price,and has promising forecasting performance and generalization ability.