Predicting stock high price using forecast error with recurrent neural network
Stock price forecasting is an eye-catching research topic. In previous works, many researchers used a single method or combination of methods to make predictions. However, accurately predicting stock prices is very difficult. To improve the predicting precision, in this study, an innovative predicti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2021-05-01
|
| Series: | Applied Mathematics and Nonlinear Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/amns.2021.2.00009 |
| _version_ | 1818745120884785152 |
|---|---|
| author | Bao Zhiguo Wei Qing Zhou Tingyu Jiang Xin Watanabe Takahiro |
| author_facet | Bao Zhiguo Wei Qing Zhou Tingyu Jiang Xin Watanabe Takahiro |
| author_sort | Bao Zhiguo |
| collection | DOAJ |
| description | Stock price forecasting is an eye-catching research topic. In previous works, many researchers used a single method or combination of methods to make predictions. However, accurately predicting stock prices is very difficult. To improve the predicting precision, in this study, an innovative prediction approach was proposed by recurrent substitution of forecast error into the historical neural network model through three steps. According to the historical data, the initial predicted value of the next day is obtained through the neural network. Then, the prediction error of the next day is obtained through the neural network according to the historical prediction error. Finally, the initial predicted value and the prediction error are added to obtain the final predicted value of the next day. We use recurrent neural network prediction methods, such as Long Short-Term Memory Network Model and Gated Recurrent Unit, which are popular in the recent neural network study. In the simulations, the past stock prices of China from June 2010 to August 2017 are used as training data, and those from September 2017 to April 2018 are used as test data. The experimental findings demonstrate that the proposed method with forecast error gives a more accurate prediction result for the stock’s high price on the next day, which indicates that the performance of the proposed one is superior to that of the traditional models without forecast error. |
| first_indexed | 2024-12-18T02:55:09Z |
| format | Article |
| id | doaj.art-41124967735c42ad8f2796dd0bc542c8 |
| institution | Directory Open Access Journal |
| issn | 2444-8656 |
| language | English |
| last_indexed | 2024-12-18T02:55:09Z |
| publishDate | 2021-05-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Mathematics and Nonlinear Sciences |
| spelling | doaj.art-41124967735c42ad8f2796dd0bc542c82022-12-21T21:23:23ZengSciendoApplied Mathematics and Nonlinear Sciences2444-86562021-05-016128329210.2478/amns.2021.2.00009Predicting stock high price using forecast error with recurrent neural networkBao Zhiguo0Wei Qing1Zhou Tingyu2Jiang Xin3Watanabe Takahiro4School of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou Henan450046, ChinaSchool of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou Henan450046, ChinaGraduate School of Information, Production and Systems, Waseda University, Kitakyushu808-0135, JapanNational Institute of Technology, Kitakyushu College, Kitakyushu802-0985, JapanGraduate School of Information, Production and Systems, Waseda University, Kitakyushu808-0135, JapanStock price forecasting is an eye-catching research topic. In previous works, many researchers used a single method or combination of methods to make predictions. However, accurately predicting stock prices is very difficult. To improve the predicting precision, in this study, an innovative prediction approach was proposed by recurrent substitution of forecast error into the historical neural network model through three steps. According to the historical data, the initial predicted value of the next day is obtained through the neural network. Then, the prediction error of the next day is obtained through the neural network according to the historical prediction error. Finally, the initial predicted value and the prediction error are added to obtain the final predicted value of the next day. We use recurrent neural network prediction methods, such as Long Short-Term Memory Network Model and Gated Recurrent Unit, which are popular in the recent neural network study. In the simulations, the past stock prices of China from June 2010 to August 2017 are used as training data, and those from September 2017 to April 2018 are used as test data. The experimental findings demonstrate that the proposed method with forecast error gives a more accurate prediction result for the stock’s high price on the next day, which indicates that the performance of the proposed one is superior to that of the traditional models without forecast error.https://doi.org/10.2478/amns.2021.2.00009stock price predictionrecurrent neural networklong short-term memory networkgated recurrent unit |
| spellingShingle | Bao Zhiguo Wei Qing Zhou Tingyu Jiang Xin Watanabe Takahiro Predicting stock high price using forecast error with recurrent neural network Applied Mathematics and Nonlinear Sciences stock price prediction recurrent neural network long short-term memory network gated recurrent unit |
| title | Predicting stock high price using forecast error with recurrent neural network |
| title_full | Predicting stock high price using forecast error with recurrent neural network |
| title_fullStr | Predicting stock high price using forecast error with recurrent neural network |
| title_full_unstemmed | Predicting stock high price using forecast error with recurrent neural network |
| title_short | Predicting stock high price using forecast error with recurrent neural network |
| title_sort | predicting stock high price using forecast error with recurrent neural network |
| topic | stock price prediction recurrent neural network long short-term memory network gated recurrent unit |
| url | https://doi.org/10.2478/amns.2021.2.00009 |
| work_keys_str_mv | AT baozhiguo predictingstockhighpriceusingforecasterrorwithrecurrentneuralnetwork AT weiqing predictingstockhighpriceusingforecasterrorwithrecurrentneuralnetwork AT zhoutingyu predictingstockhighpriceusingforecasterrorwithrecurrentneuralnetwork AT jiangxin predictingstockhighpriceusingforecasterrorwithrecurrentneuralnetwork AT watanabetakahiro predictingstockhighpriceusingforecasterrorwithrecurrentneuralnetwork |