A dynamic clustering ensemble learning approach for crude oil price forecasting

Accurate oil price forecasts matter, yet the nonstationarity of oil prices makes forecasting a challenging task. In this study, we propose a dynamic ensemble forecasting method for nonstationary oil prices using clustering approaches. Specifically, clustering is embedded in the ensemble forecasting framework, whereby the given period of historical observations is automatically classified into several clusters according to the data characteristics. This classification provides a solid groundwork for dynamically evaluating individual forecasting models in a targeted manner. We then propose a clustering-based regular increasing monotone weight assignment strategy that removes the influence of outliers and assigns appropriate weights to each forecasting model, thereby balancing the competitiveness and robustness of the proposed ensemble model. We verify the competitiveness and robustness of the proposed model by using West TX Intermediate oil prices. Results show that the proposed model significantly outperforms benchmarks and state-of-the-art methods in terms of horizontal and directional accuracy and is thus competitive. The robustness of the proposed model is validated using scenarios involving parameter variation and data missing assumptions. In summary, we present a model with promising effectiveness in promoting prediction performance in forecasting oil prices.

Automated summary

In this study, a dynamic ensemble forecasting method using clustering approaches is proposed for nonstationary oil prices. Clustering is employed to classify historical observations into clusters, providing a targeted evaluation of individual forecasting models. The proposed model includes a clustering-based weight assignment strategy to balance competitiveness and robustness. Results show that the proposed model outperforms benchmarks and state-of-the-art methods, indicating its competitiveness and robustness. The effectiveness of the proposed model is validated through parameter variation and data missing scenarios, highlighting its potential in improving oil price prediction performance.