Forecasting crude oil price with a new hybrid approach and multi-source data. (May 2021)

• Record Type: Journal Article
• Authors: Yang, Yifan; Guo, Ju'e; Sun, Shaolong; Li, Yixin
• Is Part Of: Engineering applications of artificial intelligence. Volume 101(2021)
• Publication Date: 2021-05
• Subjects: Crude oil price forecasting -- GSVI data -- Kernel extreme learning machine -- Herd behavior -- Divide and conquer; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104217
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Faced with the growing research toward crude oil price fluctuations influential factors following the accelerated development of Internet technology, accessible data such as Google search volume index (GSVI) are increasingly quantified and incorporated into forecasting approaches. In this study, we apply multi-scale data that including both traditional economic data and GSVI data reflecting macro and micro mechanisms affecting crude oil price respectively, so as to reduce the forecasting deviation and improve the forecasting accuracy at source. In addition, a new hybrid approach: K-means＋KPCA＋KELM based on "divide and conquer" strategy is proposed for deeply exploring the information of above multi-data so that improve monthly crude oil price forecasting accuracy. Empirical results can be analyzed from data and method levels. At the data level, GSVI data perform better than economic data in level forecasting accuracy but with opposite performance in directional forecasting accuracy because of "Herd Behavior", while hybrid data combined their advantages and obtain best forecasting performance in both level and directional accuracy. At the method level, the approaches with "divide and conquer" strategy gain a better forecasting performance, which demonstrates that "divide and conquer" strategy can effectively improve the forecasting performance. Highlights: Based on related searches function, a systematic way is used to select GSVI terms. KPCA is used to combine independent variables into a few efficiency composite indexes. A new hybrid approach: K-means + KPCA + KELM is proposed to forecast crude oil price. Empirical results verify that our new proposed approach and dataset performs better.