مدیریت کیفیت سبد بهینه سهام با استفاده از ترکیب مدل مارکوییتز با روش‌های ماشین بردار پشتیبان، تحلیل پوششی داده‌ها و دی بی اسکن

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه حسابداری، واحد شهرکرد، دانشگاه آزاد اسلامی، شهرکرد، ایران.

2 گروه حسابداری، واحد تهران غرب، دانشگاه آزاد اسلامی، تهران، ایران.

3 گروه حسابداری، دانشگاه اصفهان، اصفهان، ایران.

چکیده
هدف: هدف پژوهش حاضر تعیین سبد بهینه سهام با استفاده از ترکیب مدل مارکوویتز با روش‌های ماشین بردار پشتیبان، تحلیل‌پوششی‌دادها و الگویتم خوشه‌بندی دی‌بی‌اسکن است. جامعه آماری پژوهش، شرکت‌های پذیرفته‌شده در بورس اوراق بهادار تهران در بازه زمانی 1391 الی 1401 است.
روش‌شناسی پژوهش: در راستای دستیابی به اهداف پژوهش برای تشکیل سبد بهینه سهام، از رویکرد کاهش ابعاد، روش‌های تحلیل‌پوششی‌دادها، ماشین بردار پشتیبان و الگوریتم‌های خوشه‌بندی دی‌بی‌اسکن استفاده شده است. نسبت‌های مالی ترازنامه‌ای، نسبت‌های مالی صورت سود زیان، نسبت‌های مالی صورت گردش وجه نقد و نسبت‌های مالی ترکیبی و ریسک و بازده بر اساس مدل ترکیبی مارکوویتز به‌عنوان ورودی مدل تهیه چهار پرتفوی استفاده شده است.
یافته‌ها: یافته‌های حاصل از پژوهش، حاکی است روش بردار پشتیبان و روﯾﮑﺮد ﭼﻬﺎرم ﮐﻪ ﺷﺎﻣﻞ مدل ترکیبی اﺳﺖ، در بهینه‌سازی ﺳﺒﺪ ﺳﻬﺎم ﻋﻤﻠﮑﺮد ﺑﻬﺘﺮی داﺷﺘﻪ اﺳﺖ.
اصالت/ارزش افزوده علمی: با توجه به نوآوری این پژوهش در به‌کارگیری مدل ترکیبی مارکوییتز، نتایج می‌تواند به سرمایه‌گذاران و تحلیل‌گران سهام در مدیریت کیفیت سبد بهینه سهام  کمک کند.

کلیدواژه‌ها


عنوان مقاله English

Optimal stock portfolio quality management using the combination of the Markowitz model with support vector machine methods, data envelopment analysis, and DB scan

نویسندگان English

Reza Khosravi 1
Jamshid Peikfalak 2
Hassan Fattahi Nafchi 3
1 Department of Accounting, Shahrekord Branch, Islamic Azad University, Shahrekord, Iran.
2 Department of Accounting, West Tehran Branch, Islamic Azad University, Tehran, Iran.
3 Department of Accounting, University of Isfahan, Isfahan, Iran.
چکیده English

Purpose: This study aims to determine the optimal stock portfolio using a combination of the Markowitz model with Support Vector Machine (SVM), Data Envelopment Analysis (DEA), and the DBSCAN clustering algorithm. The statistical population consists of companies listed on the Tehran Stock Exchange from 2012 to 2022.
Methodology: To achieve the research objectives and form an optimal stock portfolio, dimensionality reduction approaches, DEA, SVM, and the DBSCAN clustering algorithm were employed. Financial ratios derived from balance sheets, income statements, and cash flow statements, as well as composite financial ratios and risk-return analysis based on the hybrid Markowitz model, were used as inputs to construct four portfolios.
Findings: The SVM method and the fourth approach, which includes the hybrid model, exhibited superior performance in optimizing the stock portfolio.
Originality/Value: Given the innovation of this research in applying the hybrid Markowitz model, the results can assist investors and stock analysts in managing the quality of an optimal stock portfolio.

کلیدواژه‌ها English

Optimal stock portfolio
Support vector machine
Data envelopment analysis
DBSCAN
Markowitz model
[1]     Halkos, G. E., & Salamouris, D. S. (2004). Efficiency measurement of the Greek commercial banks with the use of financial ratios: A data envelopment analysis approach. Management accounting research, 15(2), 201–224. https://doi.org/10.1016/j.mar.2004.02.001
[2]     Rasoulzadeh, M., Edalatpanah, S. A., Fallah, M., & Najafi, S. E. (2024). Trapezoidal fuzzy efficiency and cross-efficiency data envelopment analysis with network structure in order to find the optimal investment portfolio. Journal of decisions and operations research, 9(4), 968-984. (In Persian). https://doi.org/10.22105/dmor.2023.396910.1743
[3]     Shabani and Zamlai, A., Lashgari, Z., & Keyqabadi, A. (2014). Ranking the top listed companies for portfolio selection using the ahp technique (Case study: Top 50 companies on the tehran stock exchange). The second national conference on applied research in management and accounting sciences (In Persian). Tehran, Iran. Civilica. https://civilica.com/doc/381802
[4]     Alizadeh, H., & Kianfar, K. (2023). Expansion of the Markowitz model in portfolio optimization considering realistic constraints. Journal of asset management and financing, 11(4), 65-92. (In Persian). https://doi.org/10.22108/amf.2024.137329.1793
[5]     Khajavi, S., & Ghayuri Moqaddam, A. (2012). DEA method of choosing optimum portfolio in accordance with stock liquidity: The case study of listed companies of Tehran Stock Exchange. Journal of accounting advances, 4(2), 27-52. (In Persian). https://doi.org/10.22099/jaa.2012.1728
[6]     Edirisinghe, N. C. P., & and Zhang, X. (2008). Portfolio selection under DEA-based relative financial strength indicators: Case of US industries. Journal of the operational research society, 59(6), 842–856. https://doi.org/10.1057/palgrave.jors.2602442
[7]     Bahramfar, N., Mehrani, S., & Ghaiyor, F. (2005). Investigating the relationship between traditional liquidity ratios and ratios derived from the cash flow statement to assess the continuity of companies’ activities. Accounting and auditing reviews, 12(2). (In Persian). https://dor.isc.ac/dor/20.1001.1.26458020.1384.12.2.3.2
[8]     Altman, E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The journal of finance, 23(4), 589–609. https://doi.org/10.2307/2978933
[9]     Tarnaud, A. C., & Leleu, H. (2018). Portfolio analysis with DEA: Prior to choosing a model. Omega, 75, 57–76. https://doi.org/10.1016/j.omega.2017.02.003
[10]   Cook, W. D., & Seiford, L. M. (2009). Data envelopment analysis (DEA)–Thirty years on. European journal of operational research, 192(1), 1–17. https://doi.org/10.1016/j.ejor.2008.01.032
[11]   Gupta, P., Mehlawat, M. K., & Saxena, A. (2013). Hybrid optimization models of portfolio selection involving financial and ethical considerations. Knowledge-based systems, 37, 318–337. https://doi.org/10.1016/j.knosys.2012.08.014
[12]   Pätäri, E., Leivo, T., & Honkapuro, S. (2012). Enhancement of equity portfolio performance using data envelopment analysis. European journal of operational research, 220(3), 786–797. https://doi.org/10.1016/j.ejor.2012.02.006
[13]   khajavi, S., Ghayomi, A., & Jafari, M. (2010). Data envelopment analysis technique: ‌A complementary method for traditional ‌analysis of financial ratios. Accounting and auditing review, 17(2), (In Persian). https://dor.isc.ac/dor/20.1001.1.26458020.1389.17.2.3.7
[14]   Guidolin, M., Panzeri, G., & Pedio, M. (2024). Machine learning in portfolio decisions. https://dx.doi.org/10.2139/ssrn.4988124
[15]   Mohammadi Jarchelou, S., Fathi Vajargah, K., & Azhdari, P. (2022). Presenting a comparative model of stock investment portfolio optimization based on Markowitz model. Journal of mathematics and modeling in finance, 2(2), 129–150. https://doi.org/10.22054/jmmf.2023.15189
[16]   Khan, H., Halabi, A. K., & Sartorius, K. (2011). The use of multiple performance measures and the balanced scorecard (BSC) in Bangladeshi firms. Journal of accounting in emerging economies, 1(2), 160–190. https://doi.org/10.1108/20421161111138512
[17]   Chaweewanchon, A., & Chaysiri, R. (2022). Markowitz mean-variance portfolio optimization with predictive stock selection using machine learning. International journal of financial studies, 10(3), 64. https://doi.org/10.3390/ijfs10030064
[18]   Salmi, T., Virtanen, I., & Yli-Olli, P. (1990). On the classification of financial ratios: A factor and transformation analysis of accural, clash flow, and market-based ratios. Vaasan yliopisto. https://b2n.ir/jt8830
[19]   Hosseini, S. R., & Hajiannejad, A. (2022). The effect of statistical distribution of financial ratios on Altman model values using monte carlo simulation. Journal of accounting knowledge, 13(3), 161–193. https://doi.org/10.22103/jak.2022.18028.3545
[20]   Bulgurcu, B. (Kiran). (2012). Application of TOPSIS technique for financial performance evaluation of technology firms in Istanbul Stock Exchange Market. Procedia-social and behavioral sciences, 62, 1033–1040. https://doi.org/10.1016/j.sbspro.2012.09.176