Forecasting stock price movement: new evidence from a novel hybrid deep learning model
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 inte...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Emerald Publishing
2022-05-01
|
| Series: | Journal of Asian Business and Economic Studies |
| Subjects: | |
| Online Access: | https://www.emerald.com/insight/content/doi/10.1108/JABES-05-2021-0061/full/pdf?title=forecasting-stock-price-movement-new-evidence-from-a-novel-hybrid-deep-learning-model |
| _version_ | 1828104871321010176 |
|---|---|
| author | Yang Zhao Zhonglu Chen |
| author_facet | Yang Zhao Zhonglu Chen |
| author_sort | Yang Zhao |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-11T09:53:42Z |
| format | Article |
| id | doaj.art-169e2d8ee1974916958910315b2f3063 |
| institution | Directory Open Access Journal |
| issn | 2515-964X |
| language | English |
| last_indexed | 2024-04-11T09:53:42Z |
| publishDate | 2022-05-01 |
| publisher | Emerald Publishing |
| record_format | Article |
| series | Journal of Asian Business and Economic Studies |
| spelling | doaj.art-169e2d8ee1974916958910315b2f30632022-12-22T04:30:41ZengEmerald PublishingJournal of Asian Business and Economic Studies2515-964X2022-05-012929110410.1108/JABES-05-2021-0061670972Forecasting stock price movement: new evidence from a novel hybrid deep learning modelYang Zhao0Zhonglu Chen1Southwest Jiaotong University, Chengdu, ChinaSouthwest Jiaotong University, Chengdu, ChinaPurpose – 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.https://www.emerald.com/insight/content/doi/10.1108/JABES-05-2021-0061/full/pdf?title=forecasting-stock-price-movement-new-evidence-from-a-novel-hybrid-deep-learning-modelstock price movementrcsnetarimacnnlstms&p 500 indexc52g11g12 |
| spellingShingle | Yang Zhao Zhonglu Chen Forecasting stock price movement: new evidence from a novel hybrid deep learning model Journal of Asian Business and Economic Studies stock price movement rcsnet arima cnn lstm s&p 500 index c52 g11 g12 |
| title | Forecasting stock price movement: new evidence from a novel hybrid deep learning model |
| title_full | Forecasting stock price movement: new evidence from a novel hybrid deep learning model |
| title_fullStr | Forecasting stock price movement: new evidence from a novel hybrid deep learning model |
| title_full_unstemmed | Forecasting stock price movement: new evidence from a novel hybrid deep learning model |
| title_short | Forecasting stock price movement: new evidence from a novel hybrid deep learning model |
| title_sort | forecasting stock price movement new evidence from a novel hybrid deep learning model |
| topic | stock price movement rcsnet arima cnn lstm s&p 500 index c52 g11 g12 |
| url | https://www.emerald.com/insight/content/doi/10.1108/JABES-05-2021-0061/full/pdf?title=forecasting-stock-price-movement-new-evidence-from-a-novel-hybrid-deep-learning-model |
| work_keys_str_mv | AT yangzhao forecastingstockpricemovementnewevidencefromanovelhybriddeeplearningmodel AT zhongluchen forecastingstockpricemovementnewevidencefromanovelhybriddeeplearningmodel |