Financial and Banking Strategic Studies

Portfolio optimization using data envelopment analysis integration with multiple data sources, with a machine learning approach in the Tehran Stock Exchange

Document Type : Original Article

Authors

Meysam Kaviani 1
Masumeh Jafari 1
Morteza Kaviani 2
Kaveh Kaviani 1

1 Department of Management and Accounting, Karaj Branch, Islamic Azad University, Karaj, Iran.

2 Department of Accounting, Shafagh Institute of Higher Education, Tonekabon, Iran.

https://doi.org/10.22105/fbs.2025.511565.1154
Abstract
Purpose: This study aims to optimize investment portfolios by combining Data Envelopment Analysis (DEA) and machine learning, using multi-source data from the Tehran Stock Exchange. The main goal is to provide an advanced model for stock selection and portfolio optimization, enabling investors to adopt strategies more efficient than traditional methods.
Methodology: First, the DEA model was used to evaluate stock efficiency based on historical returns and asset correlations. Then, using a Support Vector Machine (SVM) and combining multiple sources of data, the trend in stock price movements is predicted. To improve the model's accuracy, random search and network methods were used to optimize the algorithm's hyperparameters. Finally, the resulting data are integrated into a portfolio optimization model, and a proposed investment strategy is formulated.
Findings: Experimental results on the Tehran Stock Exchange data showed that the proposed model can improve investment strategy performance compared to traditional methods. Sharpe and Sortino ratios indicate that the proposed model outperforms the minimum global variance strategy. It was also found that a low-diversity investment strategy can be more efficient than a fully diversified one.
Originality/Value: This study proposes a new approach to stock selection and portfolio optimization by combining DEA and machine learning. The use of multi-source data and advanced machine learning methods improves the accuracy of investor forecasting and decision-making, paving the way for future research in areas such as fuzzy models, meta-heuristic algorithms, and the analysis of relationships among financial indicators.

Keywords

Data envelopment analysis
Portfolio optimization
Machine learning
Multiple data sources

Subjects

[1]     Markowitz, H. (1952). Portfolio selection. JSTOR, 7(1), 77–91. https://doi.org/10.2307/2975974
[2]     Keynes, J. M., Johnson, E. & Moggridge, D. (2012). The collected writings of John Maynard Keynes. New York: Cambridge University Press. https://www.amazon.co.za/Collected-Writings-John-Maynard-Keynes/dp/110761046X
[3]     Uppal, R., & Wang, T. (2003). Model misspecification and underdiversification. The journal of finance, 58(6), 2465–2486. https://doi.org/10.1046/j.1540-6261.2003.00612.x
[4]     Boyle, P., Garlappi, L., Uppal, R., & Wang, T. (2012). Keynes meets Markowitz: The trade-off between familiarity and diversification. Management science, 58(2), 253–272. https://doi.org/10.1287/mnsc.1110.1349
[5]     Liu, H. (2014). Solvency constraint, underdiversification, and idiosyncratic risks. Journal of financial and quantitative analysis, 49(2), 409–430. https://doi.org/10.1017/S0022109014000271
[6]     Guidolin, M., & Liu, H. (2016). Ambiguity aversion and underdiversification. Journal of financial and quantitative analysis, 51(4), 1297–1323. https://doi.org/10.1017/S0022109016000466
[7]     Florentsen, B., Nielsson, U., Raahauge, P., & Rangvid, J. (2019). The aggregate cost of equity underdiversification. Financial review, 54(4), 833–856. https://doi.org/10.1111/fire.12212
[8]     Amiri, M., Darestani Farahani, A., & Mahboob-Ghodsi, M. (2017). Multi-criteria decision-making. Kian University Press. (In Persian). https://B2n.ir/z91916
[9]     Edirisinghe, N. C. P., & Zhang, X. (2007). Generalized DEA model of fundamental analysis and its application to portfolio optimization. Journal of banking & finance, 31(11), 3311–3335. https://doi.org/10.1016/j.jbankfin.2007.04.008
[10]   Chen, H. H. (2008). Stock selection using data envelopment analysis. Industrial management & data systems, 108(9), 1255–1268. https://doi.org/10.1108/02635570810914928
[11]   Skrinjaric, T. (2014). Investment strategy on the zagreb stock exchange based on dynamic DEA. The institute of economics, 16(1), 129–160. https://ideas.repec.org/a/iez/survey/ces-v16_04-2014_skrinjaric.html
[12]   Huang, C. Y., Chiou, C. C., Wu, T. H., & Yang, S. C. (2015). An integrated DEA-MODM methodology for portfolio optimization. Operational research, 15, 115–136. https://doi.org/10.1007/s12351-014-0164-7
[13]   M Gardijan., & Škrinjarić, T. (2015). Equity portfolio optimization: A DEA based methodology applied to the Zagreb Stock Exchange. ResearchGate, 16(2), 405–417. https://doi.org/10.17535/crorr.2015.0031
[14]   Weng, B., Ahmed, M. A., & Megahed, F. M. (2017). Stock market one-day ahead movement prediction using disparate data sources. Expert systems with applications, 79, 153–163. https://doi.org/10.1016/j.eswa.2017.02.041
[15]   Basak, S., Kar, S., Saha, S., Khaidem, L., & Dey, S. R. (2019). Predicting the direction of stock market prices using tree-based classifiers. The north American journal of economics and finance, 47, 552–567. https://doi.org/10.1016/j.najef.2018.06.013
[16]   Mohammadi, S. (2004). Technical analysis in Tehran stock exchange. Financial research journal, 6(1), 97–129. (In Persian). https://civilica.com/doc/1395623/
[17]   Kass, G. V. (1980). An exploratory technique for investigating large quantities of categorical data. Journal of the royal statistical society: Series C (applied statistics), 29(2), 119–127. https://doi.org/10.2307/2986296
[18]   Branda, M. (2015). Diversification-consistent data envelopment analysis based on directional-distance measures. Omega, 52, 65–76. https://doi.org/10.1016/j.omega.2014.11.004
[19]   Choi, H. S., & Min, D. (2017). Efficiency of well-diversified portfolios: Evidence from data envelopment analysis. Omega, 73, 104–113. https://doi.org/10.1016/j.omega.2016.12.008
[20]   Lin, R., & Li, Z. (2020). Directional distance based diversification super-efficiency DEA models for mutual funds. Omega, 97, 102096. https://doi.org/10.1016/j.omega.2019.08.003
[21]   Xiao, H., Ren, T., & Ren, T. (2020). Estimation of fuzzy portfolio efficiency via an improved DEA approach. INFOR: information systems and operational research, 58(3), 478–510. https://doi.org/10.1080/03155986.2020.1734904
[22]   Liu, W., Zhou, Z., Liu, D., & Xiao, H. (2015). Estimation of portfolio efficiency via DEA. Omega, 52, 107–118. https://doi.org/10.1016/j.omega.2014.11.006
[23]   Zhou, Z., Jin, Q., Xiao, H., Wu, Q., & Liu, W. (2018). Estimation of cardinality constrained portfolio efficiency VIA segmented DEA. Omega, 76, 28–37. https://doi.org/10.1016/j.omega.2017.03.006
[24]   Hosseinzadeh Lotfi, F., Jahanshahloo, G. R., Khodabakhshi, M., Rostamy-Malkhlifeh, M., Moghaddas, Z., & Vaez-Ghasemi, M. (2013). A review of ranking models in data envelopment analysis. Journal of applied mathematics, 2013(1), 492421. https://doi.org/10.1155/2013/492421
[25]   Zhou, Z., Xiao, H., Jin, Q., & Liu, W. (2018). DEA frontier improvement and portfolio rebalancing: An application of China mutual funds on considering sustainability information disclosure. European journal of operational research, elsevier, 269(1), 111-131. https://doi.org/10.1016/j.ejor.2017.07.010
[26]   Kerstens, K., Mounir, A., & de Woestyne, I. (2011). Non-parametric frontier estimates of mutual fund performance using C-and L-moments: some specification tests. Journal of banking & finance, 35(5), 1190–1201. https://doi.org/10.1016/j.jbankfin.2010.09.030
[27]   Lamb, J. D., & Tee, K. H. (2012). Data envelopment analysis models of investment funds. European journal of operational research, 216(3), 687–696. https://doi.org/10.1016/j.ejor.2011.08.019
[28]   Michaud, R. O. (1989). The Markowitz optimization enigma: is ‘optimized’optimal? Financial analysts journal, 45(1), 31–42. https://doi.org/10.2469/faj.v45.n1.31
[29]   DeMiguel, V., Garlappi, L., & Uppal, R. (2009). Optimal versus naive diversification: How inefficient is the 1/N portfolio strategy? The review of financial studies, 22(5), 1915–1953. https://doi.org/10.1093/rfs/hhm075
[30]   Tu, J., & Zhou, G. (2011). Markowitz meets Talmud: A combination of sophisticated and naive diversification strategies. Journal of financial economics, 99(1), 204–215. https://doi.org/10.1016/j.jfineco.2010.08.013
[31]   Beale, E. M. L., & Forrest, J. J. H. (1976). Global optimization using special ordered sets. Mathematical programming, 10, 52–69. https://doi.org/10.1007/BF01580653
Financial and Banking Strategic Studies
Volume 3, Issue 1
Spring 2025
Pages 41-55

Home

Indexing and Abstracting

Guide for Authors

Editorial Board

Submit Manuscript

Contact Us