Forecasting crude oil prices is an essential research field in the international bulk commodities market. However, price movements present more complex nonlinear behavior due to an increasingly diverse range of risk factors. To achieve better accuracy, this study explores a novel multiscale hybrid paradigm to estimate crude oil prices. The method takes advantage of the variational mode decomposition method to decompose the crude oil price into several simple models, which can be explained using regular factors, irregular factors and trends. Data characteristic analysis is conducted to identify the complexity of different components of the time series. It is important for a multiscale model to select an appropriate model to produce the optimal forecasts. Thus, the final forecasted values are generated by reconstituting all these forecasting items. By investigating the West Texas Intermediate and Brent crude oil prices, this paper presents how data characteristic identification and analysis are conducted in a multiscale paradigm. The empirical analysis proves that the proposed model can achieve superior forecasting results, which indicates the effectiveness of the multiscale model at forecasting complex time series, especially crude oil prices.

预测原油价格是国际大宗商品市场的一个重要研究领域。然而，由于风险因素的范围越来越广，价格变动呈现出更复杂的非线性行为。为了获得更高的准确性，本研究探索了一种新的多尺度混合范式来估计原油价格。该方法利用变分模式分解方法将原油价格分解为几个简单的模型，可以用规则因子、不规则因子和趋势来解释。进行数据特征分析，识别时间序列不同分量的复杂度。对于多尺度模型来说，选择合适的模型来产生最佳预测非常重要。因此，最终预测值是通过重新构建所有这些预测项目而生成的。本文通过调查西德克萨斯中质原油和布伦特原油价格，展示了如何在多尺度范式下进行数据特征识别和分析。实证分析表明，该模型能够取得较好的预测结果，表明多尺度模型在预测复杂时间序列，尤其是原油价格方面的有效性。