Forecasting Crude Oil Prices: A Deep Learning based Model

Yanhui Chen; Kaijian He; Geoffrey K.F. Tso

doi:10.1016/j.procs.2017.11.373

Forecasting Crude Oil Prices: A Deep Learning based Model

Yanhui Chen, Kaijian He^*, Geoffrey K.F. Tso

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

115 Citations (Scopus)

391 Downloads (CityUHK Scholars)

Abstract

With the popularity of the deep learning model in the engineering fields, it has attracted significant research interests in the economic and finance fields. In this paper, we use the deep learning model to capture the unknown complex nonlinear characteristics of the crude oil price movement. We further propose a new hybrid crude oil price forecasting model based on the deep learning model. Using the proposed model, major crude oil price movement is analyzed and modeled. The performance of the proposed model is evaluated using the price data in the WTI crude oil markets. The empirical results show that the proposed model achieves the improved forecasting accuracy.

Original language	English
Pages (from-to)	300-307
Journal	Procedia Computer Science
Volume	122
Online published	12 Dec 2017
DOIs	https://doi.org/10.1016/j.procs.2017.11.373
Publication status	Published - 2017
Event	The Fifth International Conference on Information Technology and Quantitative Management (ITQM 2017) - http://itqm-meeting.org/2017/, New Delhi, India Duration: 8 Dec 2017 → 10 Dec 2017 Conference number: 5th

Research Keywords

ARMA model
Crude oil price forecasting
Deep Learning model
Random Walk model

Publisher's Copyright Statement

This full text is made available under CC-BY-NC-ND 4.0. https://creativecommons.org/licenses/by-nc-nd/4.0/

Access Output

10.1016/j.procs.2017.11.373

19554601.pdfFinal Published version, 463 KBLicence: CC BY-NC-ND

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{43f28f506c134ff5a02ebb87b4c67a24,

title = "Forecasting Crude Oil Prices: A Deep Learning based Model",

abstract = "With the popularity of the deep learning model in the engineering fields, it has attracted significant research interests in the economic and finance fields. In this paper, we use the deep learning model to capture the unknown complex nonlinear characteristics of the crude oil price movement. We further propose a new hybrid crude oil price forecasting model based on the deep learning model. Using the proposed model, major crude oil price movement is analyzed and modeled. The performance of the proposed model is evaluated using the price data in the WTI crude oil markets. The empirical results show that the proposed model achieves the improved forecasting accuracy.",

keywords = "ARMA model, Crude oil price forecasting, Deep Learning model, Random Walk model",

author = "Yanhui Chen and Kaijian He and Tso, {Geoffrey K.F.}",

year = "2017",

doi = "10.1016/j.procs.2017.11.373",

language = "English",

volume = "122",

pages = "300--307",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier B.V.",

note = "The Fifth International Conference on Information Technology and Quantitative Management (ITQM 2017), ITQM 2017 ; Conference date: 08-12-2017 Through 10-12-2017",

}

TY - JOUR

T1 - Forecasting Crude Oil Prices

T2 - The Fifth International Conference on Information Technology and Quantitative Management (ITQM 2017)

AU - Chen, Yanhui

AU - He, Kaijian

AU - Tso, Geoffrey K.F.

N1 - Conference code: 5th

PY - 2017

Y1 - 2017

N2 - With the popularity of the deep learning model in the engineering fields, it has attracted significant research interests in the economic and finance fields. In this paper, we use the deep learning model to capture the unknown complex nonlinear characteristics of the crude oil price movement. We further propose a new hybrid crude oil price forecasting model based on the deep learning model. Using the proposed model, major crude oil price movement is analyzed and modeled. The performance of the proposed model is evaluated using the price data in the WTI crude oil markets. The empirical results show that the proposed model achieves the improved forecasting accuracy.

AB - With the popularity of the deep learning model in the engineering fields, it has attracted significant research interests in the economic and finance fields. In this paper, we use the deep learning model to capture the unknown complex nonlinear characteristics of the crude oil price movement. We further propose a new hybrid crude oil price forecasting model based on the deep learning model. Using the proposed model, major crude oil price movement is analyzed and modeled. The performance of the proposed model is evaluated using the price data in the WTI crude oil markets. The empirical results show that the proposed model achieves the improved forecasting accuracy.

KW - ARMA model

KW - Crude oil price forecasting

KW - Deep Learning model

KW - Random Walk model

UR - http://www.scopus.com/inward/record.url?scp=85040312106&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85040312106&origin=recordpage

U2 - 10.1016/j.procs.2017.11.373

DO - 10.1016/j.procs.2017.11.373

M3 - RGC 21 - Publication in refereed journal

SN - 1877-0509

VL - 122

SP - 300

EP - 307

JO - Procedia Computer Science

JF - Procedia Computer Science

Y2 - 8 December 2017 through 10 December 2017

ER -

Forecasting Crude Oil Prices: A Deep Learning based Model

Abstract

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this