Investigation of diversity strategies in RVFL network ensemble learning for crude oil price forecasting
- PDF / 775,896 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 55 Downloads / 211 Views
(0123456789().,-volV)(0123456789().,-volV)
METHODOLOGIES AND APPLICATION
Investigation of diversity strategies in RVFL network ensemble learning for crude oil price forecasting Lean Yu1,3
•
Yao Wu2 • Ling Tang1 • Hang Yin3 • Kin Keung Lai4
Ó Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract To address the drawback of single machine learning prediction model which cannot capture the complex hidden factors of crude oil price, ensemble learning method has been widely verified as an excellent solution for crude oil price forecasting. In ensemble learning, diversity strategy is one of the most important determinants to obtain good performance. So, this study introduced the promisingly efficient and fast RVFL network as base models to the framework of ensemble learning and explored diversity strategies in the proposed RVFL network ensemble forecasting model to obtain good performance. Specifically, the impacts of five different strategies including data quantity diversity, sampling interval diversity, parameter diversity, ensemble number diversity and ensemble method diversity on the performance of RVFL network ensemble learning have been examined and analyzed. Experimental results found that the accuracy of ensemble learning models would be increased if diversity strategies were carefully selected. Moreover, the proposed multistage nonlinear RVFL network ensemble forecasting model was consistently better than that of single RVFL network model in terms of the same measurements. Keywords RVFL network Ensemble learning Diversity strategy Crude oil price forecasting
1 Introduction Crude oil price is always playing an important role in global economy, thus an accurate prediction of crude oil price will help oil related sector to reduce losses and improve profits. Due to the instability, complexity and volatility of oil price, many machine learning models (Li and Wang 2020; Fan et al. 2016), i.e., back-propagation
Communicated by V. Loia. & Lean Yu [email protected] & Kin Keung Lai [email protected] 1
School of Economics and Management, Beijing University of Chemical Technology, Beijing 100029, China
2
School of Management and Economics, Beijing Institute of Technology, Beijing 100081, China
3
School of Economics and Management, Harbin Engineering University, Harbin 150001, China
4
College of Economics, Shenzhen University, Shenzhen 518060, China
neural networks, support vector regression, with good performance for complex system modeling are used to capture the complex hidden factors of crude oil price (Mejdoub and Ghorbel 2018). However, the performance of single machine learning models is instable owing to the insufficient training sample set, unpredictable noise sample, wrong training parameters settings (Tang et al. 2018), i.e., the number of hidden neurons, the number of iterations, learning rate and initialization condition, we cannot get the best prediction values from a limited number of single models. In this context, ensemble learning by integrating the outputs of numerous
Data Loading...
