基于模型和算法的量化投资方法股票预测研究综述

doi:10.3778/j.issn.1002-8331.2501-0157

摘要/Abstract

摘要： 股票价格预测一直是金融研究热点领域。近年来，量化投资方法凭借其客观性、系统性与高效性，逐渐成为股票市场研究的主流方向。随着大数据时代的到来，海量、多源、异构的数据为市场建模与决策提供了丰富的信息基础，有效融合多模态数据已成为提升预测准确性的关键路径。系统梳理了量化投资方法的理论演进，回顾了机器学习在股票预测中的应用发展。围绕数据、模型与算法三个维度，对近年来基于量化方法的研究成果进行了综述，深入分析并比较了不同研究在方法创新与技术实现上的差异与优势。此外，还探讨了当前研究中面临的挑战与局限，归纳总结了现有实践经验，并对多模态异构数据融合、弱信号挖掘、迁移学习及组合权重优化等研究方向进行了深入分析与展望。

关键词: 量化投资, 股票预测, 机器学习, 自然语言处理

Abstract: Stock price prediction remains a critical topic in financial research. In recent years, quantitative investment methods have gained prominence for their objectivity, systematic structure, and efficiency. The proliferation of large-scale, multi-source, and heterogeneous data in the era of big data provides a rich foundation for market modeling and decision-making. Effectively integrating multimodal data has become essential for improving prediction accuracy. This paper reviews the theoretical evolution of quantitative investment methods and examines the development of machine learning applications in stock prediction. From the perspectives of data, models, and algorithms, it surveys recent research outcomes, analyzing and comparing differences in methodological innovations and technical implementations. Challenges and limitations in current research are discussed, along with a summary of practical insights. Future directions such as multimodal data integration, weak signal mining, transfer learning, and portfolio weight optimization are also explored.

Key words: quantitative investment, stock forecast, machine learning, natural language processing

李子煜, 张金珠, 高青山. 基于模型和算法的量化投资方法股票预测研究综述[J]. 计算机工程与应用, 2025, 61(19): 1-11.

LI Ziyu, ZHANG Jinzhu, GAO Qingshan. Review on Stock Prediction Based on Models and Algorithms Within Quantitative Investment Methods[J]. Computer Engineering and Applications, 2025, 61(19): 1-11.

参考文献

[1] 丁鹏. 量化投资: 策略与技术[M]. 北京: 电子工业出版社, 2016.
DING P. Quantitative investment[M]. Beijing: Publishing House of Electronics Industry, 2016.
[2] TSAI M C, CHENG C H, TSAI M I. A multifactor fuzzy time-series fitting model for forecasting the stock index[J]. Symmetry, 2019, 11(12): 1474.
[3] AYALA J, GARCíA-TORRES M, NOGUERA J L V, et al. Technical analysis strategy optimization using a machine learning approach in stock market indices[J]. Knowledge-Based Systems, 2021, 225: 107119.
[4] LEE M C, CHANG J W, YEH S C, et al. Applying attention-based BiLSTM and technical indicators in the design and performance analysis of stock trading strategies[J]. Neural Computing and Applications, 2022, 34(16): 13267-13279.
[5] CHANDAR S K. Convolutional neural network for stock trading using technical indicators[J]. Automated Software Engineering, 2022, 29(1): 16.
[6] CARPENTER J N, LU F Z, WHITELAW R F. The real value of China’s stock market[J]. Journal of Financial Economics, 2021, 139(3): 679-696.
[7] 姜富伟, 胡逸驰, 黄楠. 央行货币政策报告文本信息、宏观经济与股票市场[J]. 金融研究, 2021(6): 95-113.
JIANG F W, HU Y C, HUANG N. Textual information of central bank monetary policy report, macroeconomy and stock market performance[J]. Journal of Financial Research, 2021(6): 95-113.
[8] MA F, GUO Y L, CHEVALLIER J, et al. Macroeconomic attention, economic policy uncertainty, and stock volatility predictability[J]. International Review of Financial Analysis, 2022, 84: 102339.
[9] ZHANG L G, CHEN W Y, HU N. Economic policy uncertainty and stock liquidity: evidence from China[J]. International Journal of Emerging Markets, 2023, 18(1): 22-44.
[10] DERAKHSHAN A, BEIGY H. Sentiment analysis on stock social media for stock price movement prediction[J]. Engineering Applications of Artificial Intelligence, 2019, 85: 569-578.
[11] HAO P Y, KUNG C F, CHANG C Y, et al. Predicting stock price trends based on financial news articles and using a novel twin support vector machine with fuzzy hyperplane[J]. Applied Soft Computing, 2021, 98: 106806.
[12] MAQBOOL J, AGGARWAL P, KAUR R, et al. Stock prediction by integrating sentiment scores of financial news and MLP-regressor: a machine learning approach[J]. Procedia Computer Science, 2023, 218: 1067-1078.
[13] DENG S K, ZHU Y K, YU Y T, et al. An integrated approach of ensemble learning methods for stock index prediction using investor sentiments[J]. Expert Systems with Applications, 2024, 238: 121710.
[14] HAN Y C, KIM J, ENKE D. A machine learning trading system for the stock market based on N-period Min-Max labeling using XGBoost[J]. Expert Systems with Applications, 2023, 211: 118581.
[15] BEHERA J, PASAYAT A K, BEHERA H, et al. Prediction based mean-value-at-risk portfolio optimization using machine learning regression algorithms for multi-national stock markets[J]. Engineering Applications of Artificial Intelligence, 2023, 120: 105843.
[16] PARRAY I R, KHURANA S S, KUMAR M, et al. Time series data analysis of stock price movement using machine learning techniques[J]. Soft Computing, 2020, 24(21): 16509-16517.
[17] ZHANG L, LI C, CHEN L, et al. A hybrid forecasting method for anticipating stock market trends via a soft-thresholding de-noise model and support vector machine (SVM)[J]. World Basic and Applied Sciences Journal, 2023, 13(2023): 597-602.
[18] GAO J Y, GUO H, XU X. Multifactor stock selection strategy based on machine learning: evidence from China[J]. Complexity, 2022, 2022(1): 7447229.
[19] GUPTA D, PRATAMA M, MA Z, et al. Financial time series forecasting using twin support vector regression[J]. Public Library of Science ONE, 2019, 14(3): e0211402.
[20] MA Y L, HAN R Z, WANG W Z. Portfolio optimization with return prediction using deep learning and machine learning[J]. Expert Systems with Applications, 2021, 165: 113973.
[21] DASH R K, NGUYEN T N, CENGIZ K, et al. Fine-tuned support vector regression model for stock predictions[J]. Neural Computing and Applications, 2023, 35(32): 23295-23309.
[22] YANG Z, ZHAO T L, WANG S W, et al. MDF-DMC: a stock prediction model combining multi-view stock data features with dynamic market correlation information[J]. Expert Systems with Applications, 2024, 238: 122134.
[23] NTI I K, ADEKOYA A F, WEYORI B A. A comprehensive evaluation of ensemble learning for stock-market prediction[J]. Journal of Big Data, 2020, 7(1): 20.
[24] NABIPOUR M, NAYYERI P, JABANI H, et al. Deep learning for stock market prediction[J]. Entropy, 2020, 22(8): 840.
[25] GYAMERAH S A, NGARE P, IKPE D. On stock market movement prediction via stacking ensemble learning method[C]//Proceedings of ?2019 IEEE Conference on Computational Intelligence for Financial Engineering & Economics, 2019.
[26] KAKADE K, JAIN I, MISHRA A K. Value-at-risk forecasting: a hybrid ensemble learning GARCH-LSTM based approach[J]. Resources Policy, 2022, 78: 102903.
[27] YUAN X H, YUAN J, JIANG T Z, et al. Integrated long-term stock selection models based on feature selection and machine learning algorithms for China stock market[J]. IEEE Access, 2020, 8: 22672-22685.
[28] HOSEINZADE E, HARATIZADEH S. CNNpred: CNN-based stock market prediction using a diverse set of variables[J]. Expert Systems with Applications, 2019, 129: 273-285.
[29] WU J R, XU K, CHEN X Y, et al. Price graphs: utilizing the structural information of financial time series for stock prediction[J]. Information Sciences, 2022, 588: 405-424.
[30] 葛业波, 刘文杰, 顾雨晨. 融合情感分析和GAN-TrellisNet的股价预测方法[J]. 计算机工程与应用, 2024, 60(12): 314-324.
GE Y B, LIU W J, GU Y C. Stock price prediction method by fusing sentiment analysis and GAN-TrellisNet[J]. Computer Engineering and Applications, 2024, 60(12): 314-324.
[31] LU M R, XU X R. TRNN: an efficient time-series recurrent neural network for stock price prediction[J]. Information Sciences, 2024, 657: 119951.
[32] LI X Y, LI Y C, YANG H Y, et al. DP-LSTM: differential privacy-inspired LSTM for stock prediction using financial news[J]. arXiv:1912.10806, 2019.
[33] LU W J, LI J Z, LI Y F, et al. A CNN-LSTM-based model to forecast stock prices[J]. Complexity, 2020, 2020(1): 6622927.
[34] SHAH J, VAIDYA D, SHAH M. A comprehensive review on multiple hybrid deep learning approaches for stock prediction[J]. Intelligent Systems with Applications, 2022, 16: 200111.
[35] 程孟菲, 高淑萍. 基于深度迁移学习的多尺度股票预测[J]. 计算机工程与应用, 2022, 58(12): 249-259.
CHENG M F, GAO S P. Multi-scale stock prediction based on deep transfer learning[J]. Computer Engineering and Applications, 2022, 58(12): 249-259.
[36] WU D M, WANG X L, WU S C. Jointly modeling transfer learning of industrial chain information and deep learning for stock prediction[J]. Expert Systems with Applications, 2022, 191: 116257.
[37] YANG M, WANG J. Adaptability of financial time series prediction based on BiLSTM[J]. Procedia Computer Science, 2022, 199: 18-25.
[38] DARADKEH M K. A hybrid data analytics framework with sentiment convergence and multi-feature fusion for stock trend prediction[J]. Electronics, 2022, 11(2): 250.
[39] 袁婧, 潘甦, 谢浩, 等. 融合投资者情绪的S_AM_BiLSTM股价预测模型[J]. 计算机工程与应用, 2024, 60(7): 274-281.
YUAN J, PAN S, XIE H, et al. Stock price prediction integrating investor sentiment based on S_AM_BiLSTM model[J]. Computer Engineering and Applications, 2024, 60(7): 274-281.
[40] ZHANG J L, YE L S, LAI Y Z. Stock price prediction using CNN-BiLSTM-attention model[J]. Mathematics, 2023, 11(9): 1985.
[41] LIU Y P, HUANG S Y, TIAN X Y, et al. A stock series prediction model based on variational mode decomposition and dual-channel attention network[J]. Expert Systems with Applications, 2024, 238: 121708.
[42] XU H F, CHAI L, LUO Z M, et al. Stock movement prediction via gated recurrent unit network based on reinforcement learning with incorporated attention mechanisms[J]. Neurocomputing, 2022, 467: 214-228.
[43] LIM Q Y E, CAO Q, QUEK C. Dynamic portfolio rebalancing through reinforcement learning[J]. Neural Computing and Applications, 2022, 34(9): 7125-7139.
[44] KABBANI T, DUMAN E. Deep reinforcement learning approach for trading automation in the stock market[J]. IEEE Access, 2022, 10: 93564-93574.
[45] JANG J, SEONG N. Deep reinforcement learning for stock portfolio optimization by connecting with modern portfolio theory[J]. Expert Systems with Applications, 2023, 218: 119556.
[46] WU Y M, FU Z J, LIU X, et al. A hybrid stock market prediction model based on GNG and reinforcement learning[J]. Expert Systems with Applications, 2023, 228: 120474.
[47] KHAN R H, MIAH J, RAHMAN M M, et al. A study of forecasting stocks price by using deep reinforcement learning[C]//Proceedings of 2023 IEEE World AI IoT Congress, 2023.
[48] ELAHI A, TAGHVAEI F. Combining financial data and news articles for stock price movement prediction using large language models[J]. arXiv:2411.01368, 2024.
[49] XIAO M, JIANG Z, QIAN L, et al. Enhancing financial time-series forecasting with retrieval-augmented large language models[J]. arXiv:2503.67890, 2025.
[50] TONG H, LI J, WU N, et al. Ploutos: towards interpretable stock movement prediction with financial large language model[J]. arXiv:2403.00782, 2024.
[51] KOA K J L, MA Y S, NG R, et al. Learning to generate explainable stock predictions using self-reflective large language models[C]//Proceedings of the ACM Web Conference 2024. New York: ACM, 2024: 4304-4315.
[52] WANG S, JI T, WANG L, et al. Stocktime: a time series specialized large language model architecture for stock price prediction[J]. arXiv:2409.08281, 2024,
[53] 胡聿文. 基于优化LSTM模型的股票预测[J]. 计算机科学, 2021, 48(S1): 151-157.
HU Y W. Stock forecast based on optimized LSTM model[J]. Computer Science, 2021, 48(S1): 151-157.
[54] 舒时克, 李路. 基于Elastic Net惩罚的多因子选股策略[J]. 统计与决策, 2021, 37(16): 157-161.
SHU S K, LI L. Multi-factor stock selection strategy based on Elastic Net punishment[J]. Statistics & Decision, 2021, 37(16): 157-161.
[55] PAN Z Y, PETTENUZZO D, WANG Y D. Forecasting stock returns: a predictor-constrained approach[J]. Journal of Empirical Finance, 2020, 55: 200-217.
[56] 徐世辉. 朴素贝叶斯法量化投资策略参数的拓展[D]. 武汉: 华中科技大学, 2019.
XU S H. The expansion of the quantitative investment strategy parameters constructed by Naive Bayesian method[D]. Wuhan: Huazhong University of Science and Technology, 2019.
[57] SASSI I, ANTER S, BEKKHOUCHA A. A graph-based big data optimization approach using hidden Markov model and constraint satisfaction problem[J]. Journal of Big Data, 2021, 8(1): 93.
[58] WANG W M, LIN W W, WEN Y M, et al. An interpretable intuitionistic fuzzy inference model for stock prediction[J]. Expert Systems with Applications, 2023, 213: 118908.
[59] WANG L, WU J B, CAO Y, et al. Forecasting renewable energy stock volatility using short and long-term Markov switching GARCH-MIDAS models: either, neither or both?[J]. Energy Economics, 2022, 111: 106056.
[60] THAKKAR A, CHAUDHARI K. Information fusion-based genetic algorithm with long short-term memory for stock price and trend prediction[J]. Applied Soft Computing, 2022, 128: 109428.
[61] CHEN W, ZHANG H Y, MEHLAWAT M K, et al. Mean-variance portfolio optimization using machine learning-based stock price prediction[J]. Applied Soft Computing, 2021, 100: 106943.
[62] CHEN S L, ZHOU C J. Stock prediction based on genetic algorithm feature selection and long short-term memory neural network[J]. IEEE Access, 2020, 9: 9066-9072.
[63] LIU X, GUO J H, WANG H, et al. Prediction of stock market index based on ISSA-BP neural network[J]. Expert Systems with Applications, 2022, 204: 117604.