Forecasting interval-valued returns of crude oil: A novel kernel-based approach

Abstract

This paper proposes a novel kernel-based generalized random interval multilayer perceptron (KG-iMLP) method for predicting high-volatility interval-valued returns of crude oil. The KG-iMLP model is constructed by utilizing the $D_K$ distance based on a kernel function, which outperforms the conventional Euclidean distance. Additionally, the optimal kernel function is estimated using the variance–covariance matrix of the prediction error, contributing to a better understanding of the overall characteristics of interval-valued data. The introduction of the kernel function renders the algorithms used for estimating machine learning parameters ineffective. Therefore, this paper further proposes a backward $D_K$ distance of accumulative error propagation algorithm to estimate both the kernel function and model parameters, which provides a feasible approach for utilizing kernel function in interval neural networks. In the empirical analysis of weekly and daily returns of WTI crude oil, the superior predictive performance of the proposed method is demonstrated, enabling stable and accurate predictions for both point values and interval values. The model exhibits consistent outstanding performance across different network structures, showcasing the potential of KG-iMLP for crude oil price forecasting.