Research on Stock Price Forecasting Model based on BiLSTM-SVR-based Hybrid Model

Songlin Zhang

doi:10.47297/wspceWSP2516-251903.20220603

PDF
导出
分享
收藏
专辑

Research on Stock Price Forecasting Model based on BiLSTM-SVR-based Hybrid Model

6卷第3期

浏览量: 0 Downloads: 23

Research on Stock Price Forecasting Model based on BiLSTM-SVR-based Hybrid Model
Research on Stock Price Forecasting Model based on BiLSTM-SVR-based Hybrid Model
Department of Mathematics and Statistics Chongqing Technology and Business University,Chongqing 400067, P. R.China
2022年6卷第3期页码：31-37
纸质出版日期： 2022-12-31 ，
DOI：10.47297/wspceWSP2516-251903.20220603
Accepted：

Scan QR Code

(2022). Research on Stock Price Forecasting Model based on BiLSTM-SVR-based Hybrid Model. 创意经济（英文版）, 6(3), 31-37.

Zhang Songlin.Research on Stock Price Forecasting Model based on BiLSTM-SVR-based Hybrid Model[J].Creative Economy,2022,06(03):31-37.
(2022). Research on Stock Price Forecasting Model based on BiLSTM-SVR-based Hybrid Model. 创意经济（英文版）, 6(3), 31-37. DOI： 10.47297/wspceWSP2516-251903.20220603.

Zhang Songlin.Research on Stock Price Forecasting Model based on BiLSTM-SVR-based Hybrid Model[J].Creative Economy,2022,06(03):31-37. DOI： 10.47297/wspceWSP2516-251903.20220603.

摘要

Abstract

In this study

we propose a combined deep learning model based on BiLSTM-SVR to predict the stock price of TSMC

an upstream company in the semiconductor industry

using three deep learning algorithms

namely Long Term Short Term Memory (LSTM)

Support Vector Regression (SVR) and BiLSTM-SVR. For BiLSTM-SVR

we chose the Root Mean Square Error (RMSE)

the Mean Absolute Error (MAE)

and the goodness of fit (R2) to measure the model performance. The BiLSTM-SVR model combination is completed by using get layer to present the output of last layer as the input of the next layer in the BiLSTM

which is fed into the SVR model for regression fitting. By comparing with the normal LSTM model

we find that the BilSTM-SVR stock price prediction model performs better among all the models in this study.

关键词

Keywords

BiLSTMSVRDeep learningStock price forecasting

references

Longxing Wang. (2019) .Global semiconductor materials market analysis. Integrated Circuit Applications, 1: 1-4.

Kogekar A.P., Nayak R., & Pati U.C. (2021). A CNN-BiLSTM-SVR based deep hybrid model for water quality forecasting of the river Ganga. In: 2021 IEEE 18th India Council International Conference (Indicon). Guwahati, India. pp. 1-6.

Yang J., De Montigny D., & Treleaven P. (2022) . ANN, LSTM, and SVR for gold price forecasting. In: 2022 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr). pp. 1-7.

Chulan Ren & Caiyan Song. (2022) Research on financial data prediction based on two-way recurrent neural network. Network Security Technology & Application, 4: 53-55.

Yiqiu Fang, Zhuang Lu & Junwei Ge. (2022). Forecasting stock prices with combined RMSE loss LSTM-CNN model. Computer Engineering and Applications, 9: 294-302.

Xin Lin & Xiaodong Zhu. (2022). LSTM stock price prediction model based on attention mechanism. Journal of Chongqing Technology and Business University(Natural Science Edition), 2: 75-82. DOI: 10.16055/j.issn.1672-058X.2022.0002.011http://dx.doi.org/10.16055/j.issn.1672-058X.2022.0002.011.

Yi Meng & Qingjuan Xu. (2021). Stock forecast based on CNN-BiLSTM and attention mechanism. Journal of Nanning Teachers Education University(Natural Science Edition), 4: 70-77. DOI: 10.16601/j.cnki.issn2096-7330.2021.04.010http://dx.doi.org/10.16601/j.cnki.issn2096-7330.2021.04.010.

Jinhai Yao. (2022). Study on stock index prediction based on ARIMA and information granular SVR combination operations. Research and Management Science, 5: 214-220.

文章被引用时，请邮件提醒。

Submit

No data

Related Author

No data

Related Institution

No data

⁰