Document Type : Research Article
Authors
1 Department of Finance, Qom Branch, Islamic Azad University, Qom, Iran
2 Department of Finance, Arak Branch, Islamic Azad University, Arak, Iran.
3 Department of Accounting, Qom Branch, Islamic Azad University, Qom, Iran.
Abstract
Given the widespread increase in classical and emerging models for asset allocation in investment portfolios available in the capital market, investors find it challenging to easily compare classical methods and machine learning techniques to identify the optimal investment combination. The aim of this research is to compare asset allocation based on the Nested Clustering Algorithm (NCO) with classical portfolios. This study has been conducted in a practical and descriptive-analytical manner, with the statistical population consisting of all companies listed on the Tehran Stock Exchange and the Iran Farabourse from 2013 to 2022. After screening, adjusted daily data from 88 companies were selected as the final sample for statistical analysis. In this context, the Kruskal-Wallis test was used to examine the hypotheses, and Python, SPSS, and Excel software were utilized. Based on the overall performance evaluation criteria for portfolios (Sharpe ratio, Sortino ratio, maximum drawdown, value at risk, and expected shortfall), the results of the hypothesis tests in this research indicate that the methods based on the Nested Clustering Optimization Algorithm outperform their classical counterparts significantly. Therefore, it can be concluded that portfolios based on machine learning algorithms perform better than classical portfolios.
Keywords
machine learning in finance: A bibliometric review, Research in International Business and
Finance, 61 (2022), 101646. https://doi.org/10.1016/j.ribaf.2022.101646
[2] E. Abounori, R. Tehrani, M. Shamani, Performance of risk-based portfolios under different conditions in the stock market (Evidence from the Iranian stock market), Financial
Economics, 45(12) (2018), 51-71. [In Persian]
[3] D. Bailey, M. Lopez de Prado ´ , An open-source implementation of the critical-line algorithm for portfolio optimization, Algorithms, 6(1) (2013), 169-196. https://doi.org/10.
3390/a6010169
[4] F. Black, R. Litterman, Asset allocation combining investor views with market equilibrium,
Journal of Fixed Income, 1(2) (1991), 7-18. https://doi.org/10.3905/jfi.1991.408013
[5] N. Bnouachir, A. Mkhadri, Efficient cluster-based portfolio optimization, Communications
in Statistics-Simulation and Computation, 50(11) (2021), 3241-3255. https://doi.org/10.
1080/03610918.2019.1621341
[6] Y. Choueifaty, Y. Coignard, Toward maximum diversification, The Journal of Portfolio
Management, 35(1) (2008), 40-51. https://doi.org/10.3905/jpm.2008.35.1.40
[7] Y. Choueifaty, T. Froidure, J. Reynier, Properties of the most diversified portfolio, Journal of Investment Strategies, 2(2) (2013), 49-70. https://doi.org/10.21314/jois.2013.033
[8] V. Ciciretti, A. Bucci, Building optimal regime-switching portfolios, The North American
Journal of Economics and Finance, 64 (2023), 101837. https://doi.org/10.1016/j.najef.
2022.101837
[9] R. Clarke, H. De Silva, S. Thorley, Portfolio constraints and the fundamental law of active management, Financial Analysts Journal, 58 (2002), 48-66. https://doi.org/10.2469/
faj.v58.n5.2468
[10] V. De Miguel, L. Garlappi, R. Uppal, Optimal versus na¨ıve diversification: How inefficient is the 1/N portfolio strategy?, Review of Financial Studies, 22(5) (2009), 1915-1953.
https://doi.org/10.1093/rfs/hhm075
[11] M. Lopez de Prado, A robust estimator of the efficient frontier, Available at SSRN, (2016).
http://dx.doi.org/10.2139/ssrn.3469961
[12] M. M. De Prado, Advances in financial machine learning, John Wiley & Sons, 2018.
[13] M. M. De Prado, Machine learning for asset managers, Cambridge University Press, 2020.
[14] A. Dogan, D. Birant, K-centroid link: a novel hierarchical clustering linkage method, Applied Intelligence, (2022), 1-24. https://doi.org/10.1007/s10489-021-02624-8
[15] F. Fabozzi, P. Kolm, D. Pachamanova, S. Focardi, Robust portfolio optimization and
management, Wiley Finance, First Edition, (2007).
[16] J. Guerard, Handbook of portfolio construction, Springer, First Edition, 2010.
[17] O. Ledoit, M. Wolf, A well-conditioned estimator for large-dimensional covariance matrices, Journal of Multivariate Analysis, 88(2) (2003), 365-411. https://doi.org/10.1016/
s0047-259x%2803%2900096-4
[18] S. Maillard, T. Roncalli, J. Te¨ıletche, The properties of equally weighted risk contribution portfolios, The Journal of Portfolio Management, 36(4) (2010), 60-70. https:
//doi.org/10.3905/jpm.2010.36.4.060
[19] H. M. Markowitz, Portfolio selection, The Journal of Finance, 7 (1952), 77-91.
[20] R. Michaud, Efficient asset allocation: a practical guide to stock portfolio optimization and
asset allocation, MA: Harvard Business School Press, (1998).
[21] S. M. Mirlouhi, N. Mohammadi Toodeshki, Optimal portfolio construction in Tehran
Stock Exchange using hierarchical and divisive clustering methods, Investment Knowledge,
9(34) (2020), 333-354. [In Persian]
[22] M. Momeni, A. Fa’al Qayoumi, Statistical analysis using SPSS, Author, Fifth Edition, 2022.
[In Persian]
[23] H. Nikumaram, F. Rahnamay Roodposhti, M. Zanjirdar, The explanation of risk and expected rate of return by using Conditional Downside Capital Assets Pricing Model, Financial
Knowledge of Securities Analysis, 3(1) (2008), 55-77. [In Persian]
[24] M. Nourahmadi, H. Sadeghi, The Application of the Main Components in Investment
Basket Management: A Case Study of Fifty Stock Exchange Companies, Budget and Finance Strategic Research, 3(1) (2022), 71-95. [In Persian] https://dor.isc.ac/dor/20.1001.
1.27171809.1401.3.1.3.6
[25] M. Nourahamadi, H. Sadeghi, A Machine Learning-Based Hierarchical Risk Parity Approach: A Case Study of Portfolio Consisting of Stocks of the Top 30 Companies on the
Tehran Stock Exchange, Financial Research Journal, 24(2) (2022), 236-256. [In Persian]
https://doi.org/10.22059/frj.2021.319092.1007146
[26] M. Nourahmadi, H. Sadeqi, Portfolio Diversification Based on Clustering Analysis, Iranian
Journal of Accounting, Auditing and Finance, 7(3) (2023), 1-16. https://doi.org/10.22067/
ijaaf.2023.43078.1092
[27] A. Y. Poletaev, E. M. Spiridonova, Hierarchical clustering as a dimension reduction
technique in the Markowitz portfolio optimization problem, Automatic Control and Computer
Sciences, 55(7) (2021), 809-815. https://doi.org/10.3103/s0146411621070270
[28] E. Y. Qian, F. Ying, J. Higgison, A dynamic decision model for portfolio investment
and assets management, Journal of Zhejiang University-SCIENCE A, 6 (2005), 163-171.
https://doi.org/10.1631/jzus.2005.as0163
[29] B. Rodr´ıguez-Camejo, Random matrix theory and nested clustered optimization on highdimensional portfolios, International Journal of Modern Physics C (IJMPC), 35(08) (2024),
1-19. https://doi.org/10.1142/S0129183124500980
[30] M. Soltani-Nejad, M. Davallou, Portfolio Optimization with Clustering Methods, Journal
of Asset Management and Financing, 4(4) (2016), 1-16. https://doi.org/10.22108/amf.
2016.21104
[31] D. Sjostrand, N. Behnejad, M. Richter ¨ , Exploration of hierarchical clustering in longonly risk-based portfolio optimization, PhD thesis, CBS, Copenhagen, 2020.
[32] H. O. Zapata, S. Mukhopadhyay, A bibliometric analysis of machine learning econometrics
in asset pricing, Journal of Risk and Financial Management, 15(11) (2022), 535. https:
//doi.org/10.3390/jrfm15110535
)