Volume 9, Issue 8
Changzhou Institute of Technology, Changzhou, Jiangsu, 213000, China
Published：30 August 2025
Scan QR Code
Zhu Xingyu.A Review of the Application of LSTM Model in Stock Price Prediction[J].Development Economics of China,2025,09(08):140-145.
Zhu Xingyu.A Review of the Application of LSTM Model in Stock Price Prediction[J].Development Economics of China,2025,09(08):140-145. DOI： 10.47297/wspdecWSP2515-797326.20250908.
Financial time series forecasting is a core issue in econometrics and statistics
and its nonlinearity
non-stationarity
and high noise characteristics pose a serious challenge to traditional statistical models such as ARIMA and GARCH. In recent years
long short-term memory networks (LSTMs) have become the mainstream model in the field of stock price prediction due to their excellent ability to capture long-term dependencies. This paper aims to systematically review and evaluate the research progress of LSTM-based stock price prediction models at home and abroad from a statistical perspective. We use the literature review method and comparative analysis method to first explain the theoretical advantages of LSTMs in dealing with the statistical characteristics of financial sequences; then we will categorize and review the existing research from three dimensions: basic application
feature enhancement
and structure optimization; finally
we analyze the relative effectiveness and applicable boundaries of LSTMs compared to traditional statistical and machine learning models. The study found that although LSTM models generally showed higher prediction accuracy
there were significant deficiencies in current research in terms of hyperparameter tuning fairness
the application of statistical significance tests (such as DM tests)
and quantification of prediction uncertainty. This paper not only constructs a knowledge graph of research in this field but also provides a theoretical framework and methodological reference for subsequent researchers that takes into account both predictive performance and statistical rigor.
BENGIOY , SIMARDP , FRASCONI P . Learning long-term dependencies with gradient descent is difficult [J ] . IEEE Transactionson Neural Networks , 1994 , 5 ( 2 ) : 157 － 166 .
Hochreiter S , Schmidhuber J . Long Short－term Memory [J ] . Neural Computation , 1997 ( 8 ) : 1735 － 1780 .
Nelson DMQ . Pereira ACM . and Oliveira RAD . Stock market's price movement prediction with LSTM neural networks [C ] . In International Joint Conference on Neural Networks (IJCNN) , IEEE , 2017 .
Fischer , T , Krauss , Christopher . Deep learning with long short-term memory networks for financial market predictions . European Journal of Operational Research , 2018 , 270 ( 2 ): 654 – 669 .
Zhang Jie . Empirical Analysis of Stock Forecasting Based on LSTM [J ] . Shandong University , 2020 .
Cui Quan . Research on Futures Price Prediction Based on Intelligent Multi-Factor Deep Learning [D ] . Nanjing University of Information Science and Technology , 2022 .
Wang Yuqian . Research on Futures Price Prediction Model of LSTM Network under Deep Learning Framework [J ] . Management and Technology of Small and Medium-sized Enterprises (Lower Edition) , 2021 ( 12 ): 137 - 139 .
Fan Junming , Liu Hongjiu , Hu Yanrong . Soybean futures price prediction Based on LSTM Deep Learning [J ] . Price Monthly , 2021 ( 02 ): 7 - 15 .
Bao W. , et al . ( 2017 ). Deep learning for event-driven stock prediction . IEEE International Conference on Data Science and Advanced Analytics , 1 - 10 .
Siami-Namini S , Namin , AS . Forecasting Economics and Financial Time Series: ARIMA vs . LSTM. arXiv e-prints , 2018 .
Geng Jingjing , Liu Yumin , Li Yang , Zhao Zheyun . Stock index prediction model Based on CNN-LSTM [J ] . Statistics and Decision , 2021 , 37 ( 05 ): 134 - 138 .
Li Hui , Hua Jinjin , Zou Borong . Stock price prediction based on RF-LSTM combined model [J ] . Journal of Henan Polytechnic University (Natural Science Edition) , 2022 , 41 ( 01 ): 136 - 142 .
Peng Yan , Liu Yuhong , Zhang Rongfen . Modeling and analysis of stock price prediction based on LSTM [J ] . Computer Engineering and Applications , 2019 , 55 ( 11 ): 209 - 212 .
Yuan Jing , Pan Su , Xie Hao , Xu Wenpeng . S_AM_BiLSTM Stock Price Prediction Model Incorporating Investor Sentiment [J ] . Computer Engineer .
Chung J. , Gulcehre C. , Cho K. , & Bengio Y . ( 2014 ). Empirical evaluation of gated recurrent neural networks on sequence modeling .
Chung J. , Gulcehre C. , Cho K. , & Bengio Y . ( 2014 ). Empirical evaluation of gated recurrent neural networks on sequence modeling .
Niu Xiaojian , Hou Qiming . Research on China Stock Price Prediction and Quantitative Strategies Based on CNN-LSTM Model [J ] . Journal of Guizhou Provincial Party School , 2025 , ( 01 ): 98 - 114 .
Hyndman R. J. , & Athanasopoulos G . ( 2018 ). Forecasting: principles and practice (3rd ed.) . Otexts .
Hewamalage P. , Bergmeir C. , & Bandara K . ( 2021 ). Recurrent neural networks for time series forecasting: Current status and future directions . International Journal of Forecasting , 37 ( 1 ), 388 - 427 .
Kearney C. , & Yang D . ( 2019 ). Volatility forecasting with GARCH models: A survey . Journal of Financial Econometrics , 17 ( 3 ), 321 - 352 .
Cao L. J. , & Tay F . E . H. ( 2003 ). Support vector machine with adaptive parameters in financial time series forecasting. IEEE Transactions on Neural Networks , 14 ( 6 ), 1506 - 1518 .
Taieb S. B. , & Atiya A . F . ( 2015 ). A bias and variance analysis for the random forests regression model: An empirical study. Neurocomputing , 160 , 226 - 236 .
Junhao Dong , Shi Liang . Hybrid CNN-LSTM-GNN Neural Network for A-Share Stock Prediction [J ] . Entropy , 2025 , 27 ( 8 ): 881 - 881 .
Guanghui Chen , Li Wang . GARCH-LSTM for Stock Price Prediction Using Sentiment Analysis [J ] . Engineering Letters , 2025 , 33 ( 7 ).
Liu Sichen . Analysis of Stock Price Prediction Methods Based on LSTM Machine Learning Models [D ] . Hangzhou Dianzi University , 2025 .
Wang Hao . Enhancing Stock Price Forecasting Accuracy Using LSTM and Bi-LSTM Models [J ] . ITM Web of Conferences , 2025 , 70 .
Jiang Shuyu . Stock Price Forecasting Based on LSTM models [J ] . Jiangsu Business Review , 2025 ,( 01 ): 83 - 86 .
Shuai Sang , Lu Li . A Stock Prediction Method Based on Heterogeneous Bidirectional LSTM [J ] . Applied Sciences , 2024 , 14 ( 20 ): 9158 - 9158 .
Shuai Sang , Lu Li . A Novel Variant of LSTM Stock Prediction Method Incorporating Attention Mechanism [J ] . Mathematics , 2024 , 12 ( 7 ).
Jyoti Prakash Behura . Stock Price Prediction using Multi-Layered Sequential LSTM [J ] . EAI Endorsed Transactions on Scalable Information Systems , 2024 , 11 ( 4 ).
Zilan Cao , Senyao Hu , Hangyu Cao , Zheng Tao . Tesla Stock Prediction Based on Twitter Comments' Sentiment Feature Extraction and Ensemble Networks [J ] . International Journal of Cooperative Information Systems , 2024 , 33 ( 04 ).
Ci Bicong , Zhang Pinyi . Financial Time Series Prediction Based on ARIMA-LSTM model [J ] . Statistics and Decision , 2022 , 38 ( 11 ): 145 - 149 .
Fang Yiqiu , Lu Zhuang , Ge Junwei . Stock price prediction combined with RMSE loss LSTM CNN model [J ] . Computer Engineering and Applications , 2022 , 58 ( 09 ): 294 - 302 .
Li , Pan Tang . Stock Price Prediction Based on Technical Analysis, fundamental analysis and deep learning [J ] . Statistics and Decision , 2022 , 38 ( 02 ): 146 - 150 .
Pham Hoang Vuong , Trinh Tan Dat , Tieu Khoi Mai , Pham Hoang Uyen , Pham The Bao . Stock-Price Forecasting Based on XGBoost and LSTM [J ] . COMPUTER SYSTEMS SCIENCE AND ENGINEERING , 2022 , 40 ( 1 ): 237 - 246 .
Cao Chaofan , Luo Zenan , Xie Jiaxin , Li Lu . Research on Stock Price prediction of MDT-CNNLSTM model [J ] . Computer Engineering and Applications , 2022 , 58 ( 05 ): 280 - 286 .
Hu Yuwen . Stock Prediction based on Optimized LSTM Model [J ] . Computer Science , 2021 , 48 ( S1 ): 151 - 157 .
Yan Zhengxu , Qin Chao , Song Gang . Stock price prediction based on Pearson Feature Selection Random Forest Model [J ] . Computer Engineering and Applications , 2021 , 57 ( 15 ): 286 - 296 .
Huang Chaobin , Cheng Ximing . Research on Stock Price Prediction Based on LSTM Neural Network [J ] . Journal of Beijing Information Science and Technology University (Natural Science Edition) , 2021 , 36 ( 01 ): 79 - 83 .
Related Author
Related Institution
京公网安备11010802024621