بهینه‌یابی سبد دارایی شامل سهام شرکت‌های منتخب در بورس اوراق بهادار تهران و رمز ارزها

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری اقتصاد دانشگاه تهران، تهران، ایران

2 دانشیار، گروه اقتصاد، دانشکده اقتصاد، دانشگاه تهران، تهران، ایران.

چکیده

در بازارهای مالی، سرمایه‌گذاران به دنبال بهینه‌سازی سبد دارایی خود با هدف حداکثرسازی بازدهی و حداقل‌سازی ریسک هستند. نظریه‌های مدرن مانند مدل میانگین-واریانس مارکویتز، باوجود موفقیت در معرفی مفاهیم اساسی مدیریت سبد، در مواجهه با بازدهی‌های غیرنرمال و بازارهای پرنوسان محدودیت‌هایی دارند. این پژوهش به بررسی عملکرد دو نوع سبد سرمایه‌گذاری شامل سبد ترکیبی (سهام بورس تهران و رمزارزها) و سبد صرفاً سهامی بورس تهران در دو حالت حداقل ریسک و پذیرش ریسک بیشتر پرداخته است. استفاده از مدل‌های پیشرفته مانند RNN و GARCH، برای پیش‌بینی بازدهی و ارزیابی ریسک، به شناسایی ترکیب‌های بهینه دارایی کمک کرده است. یافته‌ها نشان می‌دهد که سبد ترکیبی در هر دو حالت بازدهی مثبت ارائه داده است: در حالت حداقل ریسک بازدهی 3% و ریسک 8% و در حالت پذیرش ریسک بیشتر بازدهی 5% و ریسک 11%. در مقابل، سبد صرفاً سهامی در حالت حداقل ریسک بازدهی منفی 3% داشته، اما در حالت پذیرش ریسک بیشتر با بازدهی 9% عملکرد بهتری نشان داده است. همچنین، همبستگی پایین میان سهام و رمزارزها تأثیر مثبتی در کاهش ریسک کلی سبد داشته است. این نتایج نشان می‌دهد که حرکت به سمت ترکیب دارایی‌های متنوع، به‌ویژه شامل رمزارزها، می‌تواند پایداری و بازدهی سبد سرمایه‌گذاری را افزایش دهد. پژوهش حاضر استفاده از روش‌های نوین بهینه‌سازی و مدیریت ریسک را برای سرمایه‌گذاران و سیاست‌گذاران مالی پیشنهاد می‌کند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Optimizing a Portfolio Comprising Selected Stocks from the Tehran Stock Exchange and Cryptocurrencies

نویسندگان [English]

  • najafali shahbazi 1
  • sajad barkhordari 2
1 PhD student in Economics, University of Tehran, Tehran, Iran
2 Associate Professor., Department of Economics, University of Tehran,
چکیده [English]

Investors in financial markets aim to optimize portfolios to maximize returns and minimize risks. Modern portfolio theories, such as Markowitz's mean-variance model, offer foundational concepts but struggle with non-normal return distributions and volatile markets. This study evaluates two portfolio types: a mixed portfolio (Tehran Stock Exchange stocks and cryptocurrencies) and a purely stock-based portfolio under minimum risk and higher risk tolerance scenarios. Advanced models like Recurrent Neural Networks (RNN) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH) were applied to predict returns and assess risks, identifying efficient asset combinations. The mixed portfolio achieved positive returns in both scenarios. In the minimum risk scenario, it delivered a 3% return with 8% risk, and in the higher risk tolerance scenario, a 5% return with 11% risk. In contrast, the purely stock-based portfolio showed a negative 3% return in the minimum risk scenario but improved in the higher risk tolerance scenario, achieving a 9% return with 10% risk. The low correlation between stocks and cryptocurrencies significantly reduced the mixed portfolio's overall risk. This research underscores the benefits of diversification by including cryptocurrencies with traditional assets, improving portfolio stability and performance. It highlights the importance of advanced techniques like RNN for return prediction and GARCH for conditional risk assessment. The findings offer actionable insights for investors and policymakers, promoting mixed portfolios for more sustainable and resilient investment strategies.

کلیدواژه‌ها [English]

  • Portfolio Optimization
  • RNN (Recurrent Neural Network)
  • GARCH
  • Cryptocurrency
  • Condition Value at Risk (CVaR)
Ardia, D., Boudt, K., Carl, P., Mullen, K., & Peterson, B. G. (2011). Differential evolution with DEoptim: an application to non-convex portfolio optimization. The R Journal, 3(1), 27–34. doi: 10.32614/RJ-2011-002.
Arsi, S., Ben Khelifa, S., Ghabri, Y., & Mzoughi, H. (2022). Cryptocurrencies: Key risks and challenges. In Cryptofinance: A new currency for a new economy (pp. 121–145). World Scientific.
Bao, T. Q., & My, B. T. T. (2019). Forecasting stock index based on hybrid artificial neural network models. Science & Technology Development Journal-Economics-Law and Management, 3(1), 52–57.
Bariviera, A. F., Basgall, M. J., Hasperué, W., & Naiouf, M. (2017). Some stylized facts of the Bitcoin market. Physica A: Statistical Mechanics and Its Applications, 484, 82–90.
Briere, M., Oosterlinck, K., & Szafarz, A. (2015). Virtual currency, tangible return: Portfolio diversification with bitcoin. Journal of Asset Management, 16, 365–373. doi: 10.1057/jam.2015.16.
Buczynski, M., & Chlebus, M. (2024). GARCHNet: Value-at-Risk Forecasting with GARCH Models Based on Neural Networks. Computational Economics, 63(5), 1949–1979.
Charfeddine, L., Benlagha, N., & Maouchi, Y. (2020). Investigating the dynamic relationship between cryptocurrencies and conventional assets: Implications for financial investors. Economic Modelling, 85, 198–217.
Doodangeh, A., Sinaei, H., & Qasemiyeh, R. (2024). Optimized portfolio model based on prediction using CNN neural network and MSAD criterion in the Tehran Stock Exchange. Strategic Budget and Finance Research, 5(3), 11–30.dor: 20.1001.1.27171809.1403.5.3.1.2 .[In Persian].
Estrada, J. (2000). The cost of equity in emerging markets: a downside risk approach.
Eskandari, R., Panahian, H., Eskandari, R., & Ghoddati, H. (2024). Evaluating the coverage capability of cryptocurrencies on investment risk in the coin and stock market in Iran. Financial Research. https://doi.org/10.22059/frj.2024.364914.1007505. [In Persian].
Fallah, S., & Mir Fayz, Sh. (2019). Comparison of the efficiency of the mean-variance model and the Fama theory in optimizing investment portfolios in the Tehran Stock Exchange. Business Management, 42(11), 128-142. [In Persian].
Fama, E. F., & French, K. R. (1996). Multifactor explanations of asset pricing anomalies. The Journal of Finance, 51(1), 55–84. doi: 10.1111/j.1540-6261.1996.tb05202.x.
Fama, E. F., & French, K. R. (1993). Common risk factors in the returns on stocks and bonds. Journal of Financial Economics, 33(1), 3–56. doi: 10.1016/0304-405X(93)90023-5.
Félez-Viñas, E., Foley, S., Karlsen, J. R., & Svec, J. (2021). Better than Bitcoin? Can cryptocurrencies beat inflation? Can Cryptocurrencies Beat Inflation.
Katina, J., Katin, I., & Komarova, V. (2024). Cryptocurrency price forecasting: a comparative analysis of autoregressive and recurrent neural network models. Entrepreneurship and Sustainability Issues., 11(4), 425–436.
Khan, F. I., Amyotte, P. R., & Amin, M. T. (2020). Advanced methods of risk assessment and management: An overview. Methods in Chemical Process Safety, 4, 1–34.
Lee, H.-H., & Su, K.-K. (2024). Asset Allocation with Cryptocurrencies. In Handbook of Investment Analysis, Portfolio Management, and Financial Derivatives: In 4 Volumes (pp. 2795–2858). World Scientific.
Letho, L., Chelwa, G., & Alhassan, A. L. (2022). Cryptocurrencies and portfolio diversification in an emerging market. China Finance Review International.
Li, L. (2002). Macroeconomic factors and the correlation of stock and bond returns. Available at SSRN 363641.
Lilhore, U. K., Manoharan, P., Sandhu, J. K., Simaiya, S., Dalal, S., Baqasah, A. M., Alsafyani, M., Alroobaea, R., Keshta, I., & Raahemifar, K. (2023). Hybrid model for precise hepatitis-C classification using improved random forest and SVM method. Scientific Reports, 13(1), 12473.
Liu, J., & Serletis, A. (2019). Volatility in the cryptocurrency market. Open Economies Review, 30(4), 779–811.
Lu, M., & Xu, X. (2024). TRNN: An efficient time-series recurrent neural network for stock price prediction. Information Sciences, 657, 119951.
Javaheri, S., Shabani, A., & Qaemi Asl, M. (2024). Investigating the spillover effect of returns in three markets: Forex, cryptocurrency, and the Tehran Stock Exchange, using the time-varying parameters VAR model (TVP-VAR). Strategic Budget and Finance Research, 5(1), 31–56.dor: 20.1001.1.27171809.1403.5.1.2.9. [In Persian]
Makarov, I., & Schoar, A. (2022). Cryptocurrencies and decentralized finance (DeFi). Brookings Papers on Economic Activity, 2022(1), 141–215.
Mandala, J., Soehaditama, J. P., Hernawan, M. A., Yulihapsari, I. U., & Sova, M. (2023). Implementing the Capital Asset Pricing Model in Forecasting Stock Returns: A Literature Review. Indonesian Journal of Business Analytics, 3(2), 171–182.
Markowitz, H. M. (1968). Portfolio selection. Yale university press.
Mousavi Loulati, S. A., Ghanbari, H., & Mohammadi, O. (1403). Optimizing the investment portfolio using the semi-variance model with emphasis on positive potential (Case study: Tehran Stock Exchange). Strategic Budget and Finance Research, 5(1), 57-78.dor: 20.1001.1.27171809.1403.5.1.3.0. [In Persian]
Peng, C., Kim, Y. S., & Mittnik, S. (2022). Portfolio Optimization on Multivariate Regime-Switching GARCH Model with Normal Tempered Stable Innovation. Journal of Risk and Financial Management, 15(5), 230. doi: 10.3390/jrfm15050230.
Rajabi Khanqah, A., Nikoomehram, H., Taqavi, M., & Mir Fayz, Sh., .(2020). Evaluation of multivariate GARCH models in estimating value at risk for currency, stock, and gold markets. Investment Knowledge, 9(34), 15-39. [In Persian].
Rockafellar, R. T., & Uryasev, S. (2000). Optimization of conditional value-at-risk. Journal of Risk, 2, 21–42. doi: 10.21314/JOR.2000.043.
Saranj, A. and Nourahmadii, M. (2016). Estimating of value at risk and expected shortfall by using conditional extreme value approach in Tehran Securities Exchange. Financial Research Journal, 18 (3), 437-460. doi: 10.22059/jfr.2016.62450[In Persian].
Tang, S. (2022). Measurement and Management of Interest Rate Risk of Commercial Banks: Based on VaR-GARCH Model of a Case Study of SHIBOR. Scientific and Social Research, 4(1), 89–100.