Search

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 DK 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 DK 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. [ABSTRACT FROM AUTHOR]

Due to the strong nonlinearity and high complexity of foreign exchange rate data, how best to accurately analyze their trends and forecast them is regarded as a challenging research topic. While such research has developed rapidly and a large number of publications have appeared, few programmatic quantitative and qualitative overviews have been compiled in the field of exchange rate. By integrating bibliometric methods with network visualization based on CiteSpace software, this study analyzed 4999 publications of exchange rate research from the Web of Science (WoS) Core Collection database during 1992 to 2021. The study summarizes the major development in exchange rate determination since Meese‐Rogoff puzzle, from New Open‐Economy Macroeconomics (NOEM) and the Foreign Exchange Market Micro‐Structure Hypotheses, to determination model based on relationship between exchange rate and commodity price. Through the study's statistical analysis, co‐occurrence, co‐citation, and co‐keywords analysis, the influential authors, research institutions, countries and regions, journals, research hotspots, and future trends in the field of exchange rate are intellectually identified over the past 30 years. As a complement to existing literature, this paper provides theoretical and practical reference for researchers and practitioners in the field of exchange rate. [ABSTRACT FROM AUTHOR]