A Gold Futures Price Forecast Model Based on SGRU-AM

As the leading component of the financial market, the price formation mechanism of gold futures has been attracting extra attention of financiers and scholars. However, the data of gold futures price belongs to time series, and its forecast is very challenging owing to its chaotic, noisy, and non-st...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jingyang Wang, Yifan Li, Tingting Wang, Jiazheng Li, Haiyao Wang, Pengfei Liu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	GRU attention mechanism gold futures time series forecast Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/febda2ac94bc4193b9babd34a55f3a52
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:febda2ac94bc4193b9babd34a55f3a52
record_format	dspace
spelling	oai:doaj.org-article:febda2ac94bc4193b9babd34a55f3a522021-11-09T00:01:42ZA Gold Futures Price Forecast Model Based on SGRU-AM2169-353610.1109/ACCESS.2021.3122140https://doaj.org/article/febda2ac94bc4193b9babd34a55f3a522021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9584877/https://doaj.org/toc/2169-3536As the leading component of the financial market, the price formation mechanism of gold futures has been attracting extra attention of financiers and scholars. However, the data of gold futures price belongs to time series, and its forecast is very challenging owing to its chaotic, noisy, and non-stationary characteristics in data. A new forecast model named SGRU-AM, based on the special gated recurrent unit (SGRU) and attention mechanism (AM) is proposed in this paper to tackle these challenges. SGRU is the rectified model of gated recurrent unit (GRU) though executing the 1-tanh function on the reset gate output of the basic GRU to transform the value range of the reset gate value and adjusting the memory ratio between the current moment and the previous moment. Firstly, SGRU has the advantage of capturing long-distance information and can forecast the closing price of gold futures in the next trading day. Then, AM is introduced to adjust the SGRU time dimension’s feature expression, so that the model can obtain more comprehensive feature information, learn the importance of current local sequence features and improve the forecast accuracy. Taking China’s gold futures as an example, the gold futures data of the Shanghai Futures Exchange are selected from January 9, 2008, to May 31, 2021. Compared with the baseline methods, the experimental results show that SGRU-AM has the best performance among all baseline models in forecast efficiency and forecast accuracy.Jingyang WangYifan LiTingting WangJiazheng LiHaiyao WangPengfei LiuIEEEarticleGRUattention mechanismgold futurestime series forecastElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 146745-146754 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	GRU attention mechanism gold futures time series forecast Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	GRU attention mechanism gold futures time series forecast Electrical engineering. Electronics. Nuclear engineering TK1-9971 Jingyang Wang Yifan Li Tingting Wang Jiazheng Li Haiyao Wang Pengfei Liu A Gold Futures Price Forecast Model Based on SGRU-AM
description	As the leading component of the financial market, the price formation mechanism of gold futures has been attracting extra attention of financiers and scholars. However, the data of gold futures price belongs to time series, and its forecast is very challenging owing to its chaotic, noisy, and non-stationary characteristics in data. A new forecast model named SGRU-AM, based on the special gated recurrent unit (SGRU) and attention mechanism (AM) is proposed in this paper to tackle these challenges. SGRU is the rectified model of gated recurrent unit (GRU) though executing the 1-tanh function on the reset gate output of the basic GRU to transform the value range of the reset gate value and adjusting the memory ratio between the current moment and the previous moment. Firstly, SGRU has the advantage of capturing long-distance information and can forecast the closing price of gold futures in the next trading day. Then, AM is introduced to adjust the SGRU time dimension’s feature expression, so that the model can obtain more comprehensive feature information, learn the importance of current local sequence features and improve the forecast accuracy. Taking China’s gold futures as an example, the gold futures data of the Shanghai Futures Exchange are selected from January 9, 2008, to May 31, 2021. Compared with the baseline methods, the experimental results show that SGRU-AM has the best performance among all baseline models in forecast efficiency and forecast accuracy.
format	article
author	Jingyang Wang Yifan Li Tingting Wang Jiazheng Li Haiyao Wang Pengfei Liu
author_facet	Jingyang Wang Yifan Li Tingting Wang Jiazheng Li Haiyao Wang Pengfei Liu
author_sort	Jingyang Wang
title	A Gold Futures Price Forecast Model Based on SGRU-AM
title_short	A Gold Futures Price Forecast Model Based on SGRU-AM
title_full	A Gold Futures Price Forecast Model Based on SGRU-AM
title_fullStr	A Gold Futures Price Forecast Model Based on SGRU-AM
title_full_unstemmed	A Gold Futures Price Forecast Model Based on SGRU-AM
title_sort	gold futures price forecast model based on sgru-am
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/febda2ac94bc4193b9babd34a55f3a52
work_keys_str_mv	AT jingyangwang agoldfuturespriceforecastmodelbasedonsgruam AT yifanli agoldfuturespriceforecastmodelbasedonsgruam AT tingtingwang agoldfuturespriceforecastmodelbasedonsgruam AT jiazhengli agoldfuturespriceforecastmodelbasedonsgruam AT haiyaowang agoldfuturespriceforecastmodelbasedonsgruam AT pengfeiliu agoldfuturespriceforecastmodelbasedonsgruam AT jingyangwang goldfuturespriceforecastmodelbasedonsgruam AT yifanli goldfuturespriceforecastmodelbasedonsgruam AT tingtingwang goldfuturespriceforecastmodelbasedonsgruam AT jiazhengli goldfuturespriceforecastmodelbasedonsgruam AT haiyaowang goldfuturespriceforecastmodelbasedonsgruam AT pengfeiliu goldfuturespriceforecastmodelbasedonsgruam
_version_	1718441444009574400

A Gold Futures Price Forecast Model Based on SGRU-AM

Ejemplares similares