Forecasting crude oil prices: a novel model combined multisource predictors, factor screening, and forecast combination

Key Points

• Crude oil prices are predicted with enhanced accuracy using a novel model that integrates multiple predictors.
• The model's results show a significant improvement in forecasting accuracy when compared to traditional methods.
• Observational analysis employs multisource predictors and factor screening to refine forecasts effectively.
• These findings support improved forecasting techniques in an essential economic sector, benefitting stakeholders.