Article Details

Title · Authors · Abstract · Keywords · DOI · References

Optimization of Investment Portfolio Based on the Extended Markowitz Model with LSTM Neural Network

WU Nan

(Amazon. com, Inc., Beijing 100025, China)

Section：Information Application · Vol. 2025, Issue 5 · Pages：159-163 · 2096-4706（2025）05-0159-05 · CLC number：TP391 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2025.05.030

Abstract

The paper conducts research on the application of the LSTM network in predicting stock prices and explores how to integrate the prediction results of the LSTM model into the traditional Markowitz portfolio optimization model. It reports the new status of the LSTM model in investment portfolio management, especially in the prediction of the volatility of expected returns. Through experiments on dataset adjustment and optimization of the number of training sessions, the research investigates the potential for improving the prediction accuracy of the model and finds that the accuracy can approach 90%. Finally, the paper conducts an analysis of the construction of the optimal investment portfolio and its returns based on the data predicted by the LSTM model.

Keywords

Artificial Intelligence; Machine Learning; Neural Network; stock price prediction; investment portfolio optimization; Markowitz

References

  1. [1] MARKOWITZ H. Portfolio Selection [J].The Journal of Finance，1952，7（1）：77-91.
  2. [2] ALOTAIBI T S，CRAVEN M J. Efficient Frontiers in Portfolio Optimisation with Minimum Proportion Constraints [C]//Proceedings of the Genetic and Evolutionary Computation Conference Companion.Prague：ACM，2019：358-359.
  3. [3] CHAKRABARTY N. Strategic Markowitz Portfolio Optimization (SMPO): A Portfolio Return Booster [C]//2019 9th Annual Information Technology，Electromechanical Engineering and Microelectronics Conference (IEMECON).Jaipur：IEEE，2019：196-200.
  4. [4] LAI Z R，YANG H. A Survey on Gaps between Mean-Variance Approach and Exponential Growth Rate Approach for Portfolio Optimization [J].ACM Computing Surveys，2023，55（2）：1-36.
  5. [5] LYU W，CUI S，LI T. Markowitz and Index Models for Optimizing Investment Portfolio Study During COVID-19 Pandemic [C]//2022 13th International Conference on E-Education, E-Business, E-Management, and E-Learning (IC4E).Tokyo：ACM，2022：500-509.
  6. [6] ZHANG Y，LI X，GUO S. Portfolio Selection Problems with Markowitz’s Mean-Variance Framework: A Review of Literature [J].Fuzzy Optimization and Decision Making，2017，17（2）：125-158.
  7. [7] FAMA E F. Efficient Capital Markets：A Review of Theory and Empirical Work [J].The Journal of Finance，1970，25（2）：383-417.
  8. [8] MALKIEL B G. The Efficient Market Hypothesis and Its Critics [J].The Journal of Economic Perspectives，2003，17（1）：23-40.
  9. [9] DIXION M F，HALPERIN I，BILOKON P. Machine Learning in Finance: From Theory to Practice [M].Cham：Springer，2020
  10. [10] WANG H M. Stock Price Prediction Based on Machine Learning Approaches [C]//Proceedings of the 3rd International Conference on Data Science and Information Technology.Xiamen：ACM，2020：1-5.
  11. [11] RANA M，UDDIN M M，HOQUE M M. Effects of Activation Functions and Optimizers on Stock Price Prediction using LSTM Recurrent Networks [C]//Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence.Normal：ACM，2019：354-358.
  12. [12] DAY M Y，LIN J T. Artificial Intelligence for ETF Market Prediction and Portfolio Optimization [C]//Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining.Vancouver：IEEE，2019：1026-1033.
  13. [13] PATIL P，WU C S M，POTIKA K，et al. Stock Market Prediction Using Ensemble of Graph Theory, Machine Learning and Deep Learning Models [C]//Proceedings of the 3rd International Conference on Software Engineering and Information Management.Sydney：ACM，2020：85-92.
  14. [14] SUN L，XU W，LIU J. Two-Channel Attention Mechanism Fusion Model of Stock Price Prediction Based on CNN-LSTM [J].ACM Transactions on Asian and Low-Resource Language Information Processing，2021，20（5）：1-12.
  15. [15] WEI D. Prediction of Stock Price Based on LSTM Neural Network [C]//2019 International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM).Dublin：IEEE，2019：544-547.
  16. [16] GUO Y Q. Stock Price Prediction Based on LSTM Neural Network: The Effectiveness of News Sentiment Analysis [C]//2020 2nd International Conference on Economic Management and Model Engineering (ICEMME).Chongqing：IEEE，2020：1018-1024.
  17. [17] BATHLA G. Stock Price Prediction Using LSTM and SVR [C]//2020 Sixth International Conference on Parallel，Distributed and Grid Computing (PDGC).Waknaghat：IEEE，2020：211-214.

About the authors

Wu Nan (1987-), female, Han ethnicity, born in Xi'an, Shaanxi Province, China, is a national first-class registered constructor with a bachelor's degree. Her research interests include machine learning, big data, and finance.