Please use this identifier to cite or link to this item:
https://digital.lib.ueh.edu.vn/handle/UEH/64425
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang Zhao | vi |
dc.contributor.other | Zhonglu Chen | vi |
dc.date.accessioned | 2022-09-20T07:58:38Z | - |
dc.date.available | 2022-09-20T07:58:38Z | - |
dc.date.issued | 2022-06 | - |
dc.identifier.issn | 2615-9104 | - |
dc.identifier.uri | http://jabes.ueh.edu.vn/Home/SearchArticle?article_Id=100fff74-f496-3c37-a36c-92da3183cddc | - |
dc.identifier.uri | https://digital.lib.ueh.edu.vn/handle/UEH/64425 | - |
dc.description.abstract | Purpose This study explores whether a new machine learning method can more accurately predict the movement of stock prices. Design/methodology/approach This study presents a novel hybrid deep learning model, Residual-CNN-Seq2Seq (RCSNet), to predict the trend of stock price movement. RCSNet integrates the autoregressive integrated moving average (ARIMA) model, convolutional neural network (CNN) and the sequence-to-sequence (Seq2Seq) long–short-term memory (LSTM) model. Findings The hybrid model is able to forecast both linear and non-linear time-series component of stock dataset. CNN and Seq2Seq LSTMs can be effectively combined for dynamic modeling of short- and long-term-dependent patterns in non-linear time series forecast. Experimental results show that the proposed model outperforms baseline models on S&P 500 index stock dataset from January 2000 to August 2016. Originality/value This study develops the RCSNet hybrid model to tackle the challenge by combining both linear and non-linear models. New evidence has been obtained in predicting the movement of stock market prices. | vi |
dc.format | Portable Document Format (PDF) | - |
dc.publisher | University of Economics Ho Chi Minh City | vi |
dc.relation.ispartof | Journal of Asian Business and Economic Studies | vi |
dc.relation.ispartofseries | JABES, Vol.29(2) | - |
dc.subject | Stock price movement | vi |
dc.subject | RCSNet | vi |
dc.subject | ARIMA | vi |
dc.subject | CNN | vi |
dc.subject | LSTM | vi |
dc.subject | S&P 500 index | vi |
dc.title | Forecasting stock price movement: new evidence from a novel hybrid deep learning model | vi |
dc.type | Journal Article | - |
dc.identifier.doi | http://10.1108/JABES-05-2021-0061 | - |
dc.format.firstpage | 91 | - |
dc.format.lastpage | 104 | - |
item.openairetype | Journal Article | - |
item.cerifentitytype | Publications | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.grantfulltext | none | - |
item.fulltext | Only abstracts | - |
Appears in Collections: | JABES in English |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.