A Functional Data Analysis Framework Incorporating Derivative Information and Mixed-Frequency Data for Predictive Modeling of Crude Oil Price

International crude oil prices are one of the important indicators in the global economy. Forecasting on crude oil prices can provide a predictive perspective for financial investment and development decision. This study explores the application of functional data analysis (FDA) techniques in the realm of crude oil price prediction, incorporating derivative information, and mixed-frequency data. The inclusion of derivative information from price trajectories is a key aspect of this study. It enriches the modeling process, offering valuable insights into rate-of-change and volatility patterns, ultimately improving predictive accuracy. In addition, the incorporation of mixed-frequency data, spanning diverse economic indicators and their respective time series, enhances the predictive accuracy of the forecasting model. To achieve a robust and interpretable decomposition of the crude oil price signal, a multivariate empirical mode decomposition (MEMD) approach is introduced. Subsequently, employing the adaptive neural fuzzy inference system to forecast submodes and aggregate them yields the ultimate prediction outcome. Empirical validation is conducted using historical Brent crude oil price datasets and robustness testing is performed using west texas intermediate (WTI) oil price data. Comparative analyses with conventional time series prediction models reveal the superiority of the proposed approach in capturing intricate temporal dynamics, irregular patterns, and abrupt changes.