A comparison of two deep learning models on the stock exchange predictions.
In this study, we introduce the deep learning approach for the time series forecasting model, particularly for the stock price prediction, using two popular deep learning methods: the long short-term memory (LSTM) networks and the gated recurrent unit (GRU) networks. The data are collected from comp...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Al-Zaytoonah University of Jordan
2023
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/105453/ http://www.i-csrs.org/Volumes/ijasca/IJASCA.230720.15.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.utm.105453 |
|---|---|
| record_format |
eprints |
| spelling |
my.utm.1054532024-04-28T09:26:54Z http://eprints.utm.my/105453/ A comparison of two deep learning models on the stock exchange predictions. Herwindiati, Dyah E. Hendryli, Janson Sarmin, Nor Haniza L Education (General) LB Theory and practice of education In this study, we introduce the deep learning approach for the time series forecasting model, particularly for the stock price prediction, using two popular deep learning methods: the long short-term memory (LSTM) networks and the gated recurrent unit (GRU) networks. The data are collected from companies in the LQ45 index of the Indonesian Stock Exchange and the deep learning models are implemented using the Python programming language and the TensorFlow library. The results are evaluated using root mean squared error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination or R2. From the experiment, we demonstrate that the LSTM model achieves RMSE 0.005844, MAPE 0.01427, R2 0.99898, and the GRU model achieves RMSE 0.005601, MAPE 0.001594, R2 0.99907 in the training and validation phase where we utilize data up to Dec 31st, 2022. Furthermore, we test the model using unseen data from PT Adaro Energy Indonesia Tbk and find the GRU model achieves better performance with R2 0.66885 compared to the LSTM with R2 0.38756. From the experiment, we find that the deep learning approach can be considered a good forecasting model. Al-Zaytoonah University of Jordan 2023 Article PeerReviewed Herwindiati, Dyah E. and Hendryli, Janson and Sarmin, Nor Haniza (2023) A comparison of two deep learning models on the stock exchange predictions. International Journal Of Advances In Soft Computing And Its Applications, 15 (2). pp. 225-234. ISSN 2074-8523 http://www.i-csrs.org/Volumes/ijasca/IJASCA.230720.15.pdf NA |
| institution |
Universiti Teknologi Malaysia |
| building |
UTM Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Teknologi Malaysia |
| content_source |
UTM Institutional Repository |
| url_provider |
http://eprints.utm.my/ |
| topic |
L Education (General) LB Theory and practice of education |
| spellingShingle |
L Education (General) LB Theory and practice of education Herwindiati, Dyah E. Hendryli, Janson Sarmin, Nor Haniza A comparison of two deep learning models on the stock exchange predictions. |
| description |
In this study, we introduce the deep learning approach for the time series forecasting model, particularly for the stock price prediction, using two popular deep learning methods: the long short-term memory (LSTM) networks and the gated recurrent unit (GRU) networks. The data are collected from companies in the LQ45 index of the Indonesian Stock Exchange and the deep learning models are implemented using the Python programming language and the TensorFlow library. The results are evaluated using root mean squared error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination or R2. From the experiment, we demonstrate that the LSTM model achieves RMSE 0.005844, MAPE 0.01427, R2 0.99898, and the GRU model achieves RMSE 0.005601, MAPE 0.001594, R2 0.99907 in the training and validation phase where we utilize data up to Dec 31st, 2022. Furthermore, we test the model using unseen data from PT Adaro Energy Indonesia Tbk and find the GRU model achieves better performance with R2 0.66885 compared to the LSTM with R2 0.38756. From the experiment, we find that the deep learning approach can be considered a good forecasting model. |
| format |
Article |
| author |
Herwindiati, Dyah E. Hendryli, Janson Sarmin, Nor Haniza |
| author_facet |
Herwindiati, Dyah E. Hendryli, Janson Sarmin, Nor Haniza |
| author_sort |
Herwindiati, Dyah E. |
| title |
A comparison of two deep learning models on the stock exchange predictions. |
| title_short |
A comparison of two deep learning models on the stock exchange predictions. |
| title_full |
A comparison of two deep learning models on the stock exchange predictions. |
| title_fullStr |
A comparison of two deep learning models on the stock exchange predictions. |
| title_full_unstemmed |
A comparison of two deep learning models on the stock exchange predictions. |
| title_sort |
comparison of two deep learning models on the stock exchange predictions. |
| publisher |
Al-Zaytoonah University of Jordan |
| publishDate |
2023 |
| url |
http://eprints.utm.my/105453/ http://www.i-csrs.org/Volumes/ijasca/IJASCA.230720.15.pdf |
| _version_ |
1797906028647415808 |
| score |
13.211869 |