An Optimal Weighted Combined Model Coupled with Feature Reconstruction and Deep Learning for Multivariate Stock Index Forecasting

Stock index prediction plays an important role in the creation of better investment strategies. However, prediction can be difficult due to the random fluctuation of financial time series. In pursuit of improved stock index prediction, a hybrid prediction model is proposed in this paper, which conta...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jujie Wang, Yinan Liao, Zhenzhen Zhuang, Dongming Gao
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	multidimensional explanatory variables feature extraction double prediction models weighted combination optimization Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/d4ab37f0a36443e1ad32f3f368fbaedc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d4ab37f0a36443e1ad32f3f368fbaedc
record_format	dspace
spelling	oai:doaj.org-article:d4ab37f0a36443e1ad32f3f368fbaedc2021-11-11T18:13:23ZAn Optimal Weighted Combined Model Coupled with Feature Reconstruction and Deep Learning for Multivariate Stock Index Forecasting10.3390/math92126402227-7390https://doaj.org/article/d4ab37f0a36443e1ad32f3f368fbaedc2021-10-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/21/2640https://doaj.org/toc/2227-7390Stock index prediction plays an important role in the creation of better investment strategies. However, prediction can be difficult due to the random fluctuation of financial time series. In pursuit of improved stock index prediction, a hybrid prediction model is proposed in this paper, which contains two-step data pretreatment, double prediction models, and smart optimization. In the data pretreatment stage, in order to carry more information about the prediction target, multidimensional explanatory variables are selected by the Granger causality test, and to eliminate data redundancy, feature extraction is inserted with the help of principal component analysis; both of these can provide a higher-quality dataset. Bi-directional long short-term memory and bi-directional gated recurrent unit network, as the concurrent prediction models, can improve not only the precision, but also the robustness of results. In the last stage, the proposed model integrates the weight optimization of the cuckoo search of the two prediction results to take advantage of both. For the model performance test, four main global stock indices are used. The experimental results show that our model performs better than other benchmark models, which indicates the potential of the proposed model for wide application.Jujie WangYinan LiaoZhenzhen ZhuangDongming GaoMDPI AGarticlemultidimensional explanatory variablesfeature extractiondouble prediction modelsweighted combination optimizationMathematicsQA1-939ENMathematics, Vol 9, Iss 2640, p 2640 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	multidimensional explanatory variables feature extraction double prediction models weighted combination optimization Mathematics QA1-939
spellingShingle	multidimensional explanatory variables feature extraction double prediction models weighted combination optimization Mathematics QA1-939 Jujie Wang Yinan Liao Zhenzhen Zhuang Dongming Gao An Optimal Weighted Combined Model Coupled with Feature Reconstruction and Deep Learning for Multivariate Stock Index Forecasting
description	Stock index prediction plays an important role in the creation of better investment strategies. However, prediction can be difficult due to the random fluctuation of financial time series. In pursuit of improved stock index prediction, a hybrid prediction model is proposed in this paper, which contains two-step data pretreatment, double prediction models, and smart optimization. In the data pretreatment stage, in order to carry more information about the prediction target, multidimensional explanatory variables are selected by the Granger causality test, and to eliminate data redundancy, feature extraction is inserted with the help of principal component analysis; both of these can provide a higher-quality dataset. Bi-directional long short-term memory and bi-directional gated recurrent unit network, as the concurrent prediction models, can improve not only the precision, but also the robustness of results. In the last stage, the proposed model integrates the weight optimization of the cuckoo search of the two prediction results to take advantage of both. For the model performance test, four main global stock indices are used. The experimental results show that our model performs better than other benchmark models, which indicates the potential of the proposed model for wide application.
format	article
author	Jujie Wang Yinan Liao Zhenzhen Zhuang Dongming Gao
author_facet	Jujie Wang Yinan Liao Zhenzhen Zhuang Dongming Gao
author_sort	Jujie Wang
title	An Optimal Weighted Combined Model Coupled with Feature Reconstruction and Deep Learning for Multivariate Stock Index Forecasting
title_short	An Optimal Weighted Combined Model Coupled with Feature Reconstruction and Deep Learning for Multivariate Stock Index Forecasting
title_full	An Optimal Weighted Combined Model Coupled with Feature Reconstruction and Deep Learning for Multivariate Stock Index Forecasting
title_fullStr	An Optimal Weighted Combined Model Coupled with Feature Reconstruction and Deep Learning for Multivariate Stock Index Forecasting
title_full_unstemmed	An Optimal Weighted Combined Model Coupled with Feature Reconstruction and Deep Learning for Multivariate Stock Index Forecasting
title_sort	optimal weighted combined model coupled with feature reconstruction and deep learning for multivariate stock index forecasting
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d4ab37f0a36443e1ad32f3f368fbaedc
work_keys_str_mv	AT jujiewang anoptimalweightedcombinedmodelcoupledwithfeaturereconstructionanddeeplearningformultivariatestockindexforecasting AT yinanliao anoptimalweightedcombinedmodelcoupledwithfeaturereconstructionanddeeplearningformultivariatestockindexforecasting AT zhenzhenzhuang anoptimalweightedcombinedmodelcoupledwithfeaturereconstructionanddeeplearningformultivariatestockindexforecasting AT dongminggao anoptimalweightedcombinedmodelcoupledwithfeaturereconstructionanddeeplearningformultivariatestockindexforecasting AT jujiewang optimalweightedcombinedmodelcoupledwithfeaturereconstructionanddeeplearningformultivariatestockindexforecasting AT yinanliao optimalweightedcombinedmodelcoupledwithfeaturereconstructionanddeeplearningformultivariatestockindexforecasting AT zhenzhenzhuang optimalweightedcombinedmodelcoupledwithfeaturereconstructionanddeeplearningformultivariatestockindexforecasting AT dongminggao optimalweightedcombinedmodelcoupledwithfeaturereconstructionanddeeplearningformultivariatestockindexforecasting
_version_	1718431913184591872

An Optimal Weighted Combined Model Coupled with Feature Reconstruction and Deep Learning for Multivariate Stock Index Forecasting

Ejemplares similares