A Hybrid Approach Integrating Multiple ICEEMDANs, WOA, and RVFL Networks for Economic and Financial Time Series Forecasting

Abstract

The fluctuations of economic and financial time series are influenced by various kinds of factors and usually demonstrate strong nonstationary and high complexity. Therefore, accurately forecasting economic and financial time series is always a challenging research topic. In this study, a novel multidecomposition and self-optimizing hybrid approach integrating multiple improved complete ensemble empirical mode decompositions with adaptive noise (ICEEMDANs), whale optimization algorithm (WOA), and random vector functional link (RVFL) neural networks, namely, MICEEMDAN-WOA-RVFL, is developed to predict economic and financial time series. First, we employ ICEEMDAN with random parameters to separate the original time series into a group of comparatively simple subseries multiple times. Second, we construct RVFL networks to individually forecast each subseries. Considering the complex parameter settings of RVFL networks, we utilize WOA to search the optimal parameters for RVFL networks simultaneously. Then, we aggregate the prediction results of individual decomposed subseries as the prediction results of each decomposition, respectively, and finally integrate these prediction results of all the decompositions as the final ensemble prediction results. The proposed MICEEMDAN-WOA-RVFL remarkably outperforms the compared single and ensemble benchmark models in terms of forecasting accuracy and stability, as demonstrated by the experiments conducted using various economic and financial time series, including West Texas Intermediate (WTI) crude oil prices, US dollar/Euro foreign exchange rate (USD/EUR), US industrial production (IP), and Shanghai stock exchange composite index (SSEC).

Information Flow from COVID‐19 Pandemic to Islamic and Conventional Equities: An ICEEMDAN‐Induced Transfer Entropy Analysis

“…e ICEEMDAN-based entropy facilitates the assessment of the amount of information flow to account for huge tails in the studied markets' equities returns across distinct time horizons. According to Wu et al [28], the ICEEMDAN decomposes time series into inherent mode functions (IMFs) at multiple time scales due to its data-intensive nature.…”

“…e decomposition methods are empirical and adaptive, and they are designed to account for nonstationary, nonlinear, and complex data while making no assumptions about their characteristics [28][29][30]. e ICEEMDAN outperforms the variational mode decomposition (VMD) [28] and wavelet-based decompositions [30].…”

“…e decomposition methods are empirical and adaptive, and they are designed to account for nonstationary, nonlinear, and complex data while making no assumptions about their characteristics [28][29][30]. e ICEEMDAN outperforms the variational mode decomposition (VMD) [28] and wavelet-based decompositions [30]. Several scholars [28,31,32] have resorted to the ICE-EMDAN technique to investigate the dynamics of economic 2 Complexity markets due to the relative advantages it possesses over other decomposition techniques from the family of the empirical mode decompositions (EMDs) of Huang [33], which are considered superior on their own notwithstanding their limitations [30].…”

“…e ICEEMDAN outperforms the variational mode decomposition (VMD) [28] and wavelet-based decompositions [30]. Several scholars [28,31,32] have resorted to the ICE-EMDAN technique to investigate the dynamics of economic 2 Complexity markets due to the relative advantages it possesses over other decomposition techniques from the family of the empirical mode decompositions (EMDs) of Huang [33], which are considered superior on their own notwithstanding their limitations [30]. e EMD, for instance, has been critiqued for a "mode mixing" issue.…”

Ultra Short-Term Wind Power Forecasting Based on Sparrow Search Algorithm Optimization Deep Extreme Learning Machine

“…In recent years, many scholars around the world have begun to study the combination of optimization algorithms and prediction models to achieve optimization of prediction model parameters [22]. Multiple algorithms such as genetic algorithm, whale optimization algorithm, differential evolution algorithm, cuckoo search algorithm, and sparrow search algorithm have been successfully used to optimize power prediction models [6,[23][24][25][26]. In [27], M. H. Ahmadi et al use genetic algorithms to optimize the hyperparameters embedded in the least-squares support vector machine model and use the size, concentration, and temperature of nanoparticles as input variables to predict the thermal conductivity of Al 2 O 3 /EG.…”