[Home ] [Archive]   [ فارسی ]  
Main Menu
Home
Journal Information
Aims& Scopes
Editorial Board
About the Journal
Journal News
Articles archive
All Issues
Current Issue
Browse by Authors
Browse by Keywords
For Authors
Call for Papers
Submission Instruction
Submission Form
For Reviewers
Reviewers Section
Registration
Registration Information
Registration Form
Contact us
Contact Information
Contact us
Site Facilities
Site map
Search contents
FAQ
Top 10 contents
Inform to friends
::
MBRI Journals

Journal of Money & Economy

AWT IMAGE

(رتبه علمی-پژوهشی)

..
Related Journals

Journal of Islamic Finance Research

AWT IMAGE

(Biannual)

..
Search in website

Advanced Search
..
Receive site information
Enter your Email in the following box to receive the site news and information.
..
:: year 19, Issue 68 (9-2026) ::
JMBR 2026, 19(68): 355-380 Back to browse issues page
Mean-variance portfolio based on covariance matrix prediction with LSTM networks using Cholesky decomposition approach
Seyfollah Heydari1 , Amir Mohammadzadeh *2 , Soheyla Khishtandar2
1- Islamic Azad University, Qazvin Branch, Faculty of Management and Accounting;
2- Islamic Azad University, Qazvin Branch, Faculty of Management and Accounting
Abstract:   (252 Views)
The Markowitz mean - variance model is based on minimizing risk at different expected return levels . However , the key to success in this approach relies on accurately predicting the return vector and the dynamic covariance matrix among assets , as these relationships are constantly changing , and understanding this dynamism is crucial for achieving an optimal portfolio . The present research utilizes Long Short - Term Memory (LSTM) networks for the dynamic predicted of the covariance matrix , with its innovaton lying in addressingthe issue of the predicted covariance matrix not being positive definite by employing the Cholesky decomposition approach . In this study , the mean - variance approach was used to optimize a portfolio consisting of 10 major Tehran Stock Exchange indices the period 1390 to1404 comparing three models : LSTM networks with Cholesky decomposition , Hidden Markov , and DCC - GARCH . The results showed that the LSTM model , with a weekly average return of 0.0050 , risk of 0.038 , Sharpe ratio of 0.13 , and cumulative teturn of 2.42 , demonstrated significant superiority over the other two models in controlling risk and profitability .This superiority stems from  LSTMs ability to model  the complex and dynamic patterns of the Iranian capital market .
Full-Text [PDF 1588 kb]   (89 Downloads)    
Type of Study: Theoretical Article | Subject: Financial Institutions and Services (G2)
Received: 2026/04/15 | Accepted: 2026/06/1 | Published: 2026/06/23
References
1. رفرنس های متنی مثل خروجی کراس رف را در اینجا وارد کرده و تایید کنید اسفندیار، م.، کرامتی، م.ع.، و غلامی جمکرانی، ر. (1401). بهینه‌سازی پورتفوی سهام در بورس اوراق بهادار تهران (کاربرد رهیافت یادگیری تقویتی). مدلسازی اقتصادی، 16(58)، 51-66.
2. اقتصاد، ا.ع. و محمدی، ع. (1402). بهینه‌سازی سبد سرمایه‌گذاری به کمک پیش‌بینی بازده مورد انتظار با استفاده از روش‌های شبکهٔ عصبی LSTM، جنگل تصادفی و. ARIMA چشم‌انداز مدیریت مالی، 13(43)، 9-28.
3. کیانی‌زاده، ح.، باغانی، ع.، و حمیدیان، م. (1402). مقایسهٔ دقت مدل‌های منتخب یادگیری ماشین جهت پیش‌بینی قیمت سهام در بورس اوراق بهادار. بورس اوراق بهادار، 16(62)، 75-102.
4. هراتی‌زاده، س.، و رضایی، ف. (1402). ارائه روشی جدید برای بهره‌گیری از یادگیری ماشین در فرآیند بهینه‌سازی سبد سهام. تصمیم‌گیری و تحقیق در عملیات، 8(2)، 527-539.
5. Agal, S., Raulji, K., & Odedra, N. D. (2025). A machine learning approach to risk based asset allocation in portfolio optimization. Scientific Reports, 15, 42263. [DOI:10.1038/s41598-025-26337-x]
6. Espiga Fernández, F., García Sánchez, Á., & Ordieres Meré, J. (2024). A systematic approach to portfolio optimization: A comparative study of reinforcement learning agents, market signals, and investment horizons. Algorithms, 17(12), 570. [DOI:10.3390/a17120570]
7. Fan, Y. (2025). Enhancing Investment Strategies with LSTM based Stock Prediction and Mean Variance Portfolio Optimization. Advances in Economics, Management and Political Sciences, 182, 110-117. [DOI:10.54254/2754-1169/2024.23667]
8. Kevin, J., & Yugopuspito, P. (2025). Hybrid LSTM and PPO networks for dynamic portfolio optimization. arXiv. [DOI:10.1145/3789982.3790022]
9. Li, H., & Liu, T. (2023). Portfolio optimization based on the LSTM forecasting model. Advances in Economics, Management and Political Sciences, 48, 97-106. [DOI:10.54254/2754-1169/48/20230431]
10. Li, X. (2025). LSTM based portfolio optimization strategy. Highlights in Business, Economics and Management, 50, 347-354. [DOI:10.54097/n4ypa255]
11. Majumder, R., Ji, Q., & Neerchal, N. K. (2024). Optimal stock portfolio selection with a multivariate hidden markov model. arXiv.
12. Taljaard, B. (2025). Regime based portfolio optimisation: A hidden Markov model approach for fixed income portfolios. European Stability Mechanism Working Paper. [DOI:10.2139/ssrn.5341853]
13.  
Send email to the article author



XML   Persian Abstract   Print



Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
year 19, Issue 68 (9-2026) Back to browse issues page
فصلنامه پژوهش‌های پولی-بانکی Journal of Monetary & Banking Research
Persian site map - English site map - Created in 0.08 seconds with 37 queries by YEKTAWEB 4774