Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models
Various deep learning techniques have recently been developed in many fields due to the rapid advancement of technology and computing power. These techniques have been widely applied in finance for stock market prediction, portfolio optimization, risk management, and trading strategies. Forecasting...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/7/4644 |
| _version_ | 1797608226759376896 |
|---|---|
| author | Hyunsun Song Hyunjun Choi |
| author_facet | Hyunsun Song Hyunjun Choi |
| author_sort | Hyunsun Song |
| collection | DOAJ |
| description | Various deep learning techniques have recently been developed in many fields due to the rapid advancement of technology and computing power. These techniques have been widely applied in finance for stock market prediction, portfolio optimization, risk management, and trading strategies. Forecasting stock indices with noisy data is a complex and challenging task, but it plays an important role in the appropriate timing of buying or selling stocks, which is one of the most popular and valuable areas in finance. In this work, we propose novel hybrid models for forecasting the one-time-step and multi-time-step close prices of DAX, DOW, and S&P500 indices by utilizing recurrent neural network (RNN)–based models; convolutional neural network-long short-term memory (CNN-LSTM), gated recurrent unit (GRU)-CNN, and ensemble models. We propose the averaging of the high and low prices of stock market indices as a novel feature. The experimental results confirmed that our models outperformed the traditional machine-learning models in 48.1% and 40.7% of the cases in terms of the mean squared error (MSE) and mean absolute error (MAE), respectively, in the case of one-time-step forecasting and 81.5% of the cases in terms of the MSE and MAE in the case of multi-time-step forecasting. |
| first_indexed | 2024-03-11T05:41:33Z |
| format | Article |
| id | doaj.art-1418f9d5346545c3a0978afbd58cfb2f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:41:33Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1418f9d5346545c3a0978afbd58cfb2f2023-11-17T16:23:31ZengMDPI AGApplied Sciences2076-34172023-04-01137464410.3390/app13074644Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble ModelsHyunsun Song0Hyunjun Choi1Department of Nano & Semiconductor Engineering, Tech University of Korea, Siheung-si 15073, Republic of KoreaDepartment of Nano & Semiconductor Engineering, Tech University of Korea, Siheung-si 15073, Republic of KoreaVarious deep learning techniques have recently been developed in many fields due to the rapid advancement of technology and computing power. These techniques have been widely applied in finance for stock market prediction, portfolio optimization, risk management, and trading strategies. Forecasting stock indices with noisy data is a complex and challenging task, but it plays an important role in the appropriate timing of buying or selling stocks, which is one of the most popular and valuable areas in finance. In this work, we propose novel hybrid models for forecasting the one-time-step and multi-time-step close prices of DAX, DOW, and S&P500 indices by utilizing recurrent neural network (RNN)–based models; convolutional neural network-long short-term memory (CNN-LSTM), gated recurrent unit (GRU)-CNN, and ensemble models. We propose the averaging of the high and low prices of stock market indices as a novel feature. The experimental results confirmed that our models outperformed the traditional machine-learning models in 48.1% and 40.7% of the cases in terms of the mean squared error (MSE) and mean absolute error (MAE), respectively, in the case of one-time-step forecasting and 81.5% of the cases in terms of the MSE and MAE in the case of multi-time-step forecasting.https://www.mdpi.com/2076-3417/13/7/4644deep learningconvolutional neural networksrecurrent neural networkslong short-term memorygated recurrent unitensemble model |
| spellingShingle | Hyunsun Song Hyunjun Choi Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models Applied Sciences deep learning convolutional neural networks recurrent neural networks long short-term memory gated recurrent unit ensemble model |
| title | Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models |
| title_full | Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models |
| title_fullStr | Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models |
| title_full_unstemmed | Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models |
| title_short | Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models |
| title_sort | forecasting stock market indices using the recurrent neural network based hybrid models cnn lstm gru cnn and ensemble models |
| topic | deep learning convolutional neural networks recurrent neural networks long short-term memory gated recurrent unit ensemble model |
| url | https://www.mdpi.com/2076-3417/13/7/4644 |
| work_keys_str_mv | AT hyunsunsong forecastingstockmarketindicesusingtherecurrentneuralnetworkbasedhybridmodelscnnlstmgrucnnandensemblemodels AT hyunjunchoi forecastingstockmarketindicesusingtherecurrentneuralnetworkbasedhybridmodelscnnlstmgrucnnandensemblemodels |