طراحی سیستم پشتیبان تصمیم‌گیری مدیریت سبد‌ سهام با بهره‌گیری از روش‌های علم ‌داده (بازار بورس اوراق بهادار تهران)

نوع مقاله : پژوهشی

نویسندگان

گروه مهندسی صنایع، دانشکده‌ی فنی مهندسی، دانشگاه میبد، یزد.

چکیده

افزایش سودآوری و کاهش میزان ریسک، مستلزم انتخاب مسیر هوشمند سرمایه‌گذاری ضمن بهره‌گیری از تحلیل داده است؛ لذا امروزه ارائه‌ی روشی در قالب سیستم پشتیبان تصمیم‌گیری مدیریت سبد‌ سهام، ضمن درک بهتر جایگاه علم ‌داده، ضروری است؛ لذا در پژوهش حاضر، علاوه‌بر دستیابی به این مهم، ضمن ترکیب روش‌های علم ‌داده با مدل مارکویتز، مدل‌های طبقه‌بندی و پیش‌بینی نیز ایجاد شده‌اند، که در تشخیص تقلب مالی شرکت‌ها مؤثر هستند. همچنین، به‌منظور خوشه‌بندی شرکت‌های فعال در بورس اوراق بهادار تهران، الگوریتم‌های سلسله‌مراتبی و کامینز استفاده شده‌اند. درخصوص طبقه‌بندی داده‌ها، الگوریتم طبقه‌بندی ماشین ‌بردار پشتیبان ‌خطی با دقت 70٪ در مقایسه با الگوریتم‌های‌ درخت ‌تصمیم، نایوبیز، نزدیک‌ترین همسایه، و پرسپترون چند‌لایه و درخصوص ساخت مدل‌های پیش‌بینی، درخت تصمیم با کمینه‌ی میزان خطا، در مقایسه با الگوریتم‌های نایوبیز، نزدیک‌ترین همسایه، پرسپترون چند‌لایه شناسایی شده‌اند. داده‌های اولیه در پژوهش حاضر، شامل 20 عنوان شاخص مالی و داده‌های روزانه‌ی قیمت سهام شرکت‌ها در فضای برنامه‌نویسی پایتون بوده‌اند. 

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Designing a Decision Support System for Portfolio Management using Data Science Methods (Tehran Stock Exchange)

نویسندگان [English]

  • Navid Javaheri
  • Najmeh Neshat
  • Abbasali Jafari Nodoushan
Department of Industrial Engineering, Faculty of Engineering, Meybod University, Meybod, Iran.
چکیده [English]

Increasing profitability and reducing risk always requires choosing a smart investment path while taking advantage of data analysis; Therefore, it is necessary to provide a technique in the form of a decision support system for stock portfolio management while better understanding the position of data science. In this research, while combining data science methods with the Markowitz model, classification and forecasting models have also been created. Detecting financial fraud of companies is also effective; Hierarchical and Cummins algorithms have also been used in order to cluster active companies in the Tehran Stock Exchange. In terms of data classification, the linear support vector machine classification algorithm has been identified with 70% accuracy in comparison with the decision tree, Nyobies, nearest neighbour, and multilayer perceptron algorithms, and in terms of building prediction models, the decision tree with the minimum amount of error, in comparison with Nyobies algorithms, is the closest Neighbor, multilayer perceptron has been identified. The primary data in the current research includes twenty titles of financial indicators and daily data of stock prices of companies in the Python programming space. It was concluded that choosing stocks from among the clusters formed by different stocks of companies will reduce the risk of diversifying the stock portfolio. The mentioned system will be able to generalize as a comprehensive model for data in different time intervals and the indicators desired by the analyst, thus helping investors in a fast and accurate analytical way. The performance of the final technique will be such that the investor first selects several desired companies according to the heard, analysis, and news; It predicts the price performance of companies; Then, it separates the companies that have succeeded in accepting the condition by using the clustering model and separates the portfolio of various stocks. It forms according to the amount of risk and expected return. Importantly, as mentioned, the presented classification and forecasting models, in addition to being used in the formation and management of the stock portfolio, will be able to be effective in predicting the possible fraud of companies.

کلیدواژه‌ها [English]

  • Portfolio management
  • modeling
  • data science
  • classification
  • clustering
  • segmentation
1. Pyle, D., 2003. Business Modeling and Data Mining. Elsevier Press, Netherlands.  https://doi.org/10.1016/B978-1-55860-653-1.X5000-3.
2. Dean, J., 2014. Big Data, Data Mining, and Machine Learning: Value Creation for Business Leaders and Practitioners. John Wiley & Sons Press, United States. ISBN: 978-1-118-69178-6. https://www.nrigroupindia.com/e-book
3.Kunnathuvalappil Hariharan, N., 2018. Applications of data mining in finance. of Innovations in Engineering Research and Technology5(2), pp.72-77. https://www.researchgate.net/publication/354224201_APP  LICATIONS_OF_DATA_MINING_IN_FINANCE.
4. Zamani, M., Pakmaram, A., Rezaei, N. and Abdi, R., 2023. The role of information behavior in financial reporting (With an emphasis on information entropy theory). J. of Nonlinear Analysis and Applications, 15(4), pp. 293-309.     https://doi.org/10.22075/IJNAA.2022.28778.3985.      [In Persian].   
5. Abdullah, Z. and Hamdan, A., 2015. Hierarchical clustering algorithms in data mining. J. of Computer and Information Engineering, 9(10), pp.2194-2199. https:doi.org/10.5281/zenodo.1109341
6. Nokart., 2021. The Difference Between Data Science And Data Mining. from ‪Nokartohttps://nokarto.com/. [In Persian].
7. Fazel Zarandi, M. and Kazemi, A., 2008. Application of rough set theory in data mining for decision support systems (DSSs). QIAU, (1), pp. 25-34.    https://civilica.com/doc/790867/ [In Persian].
8. Dastgir, Sh., 2019. Data mining technology, a new approach in the financial field. Auditing Knowledge, 11(4), 0-0.
9. VanderPlas, J., 2016. Python data science handbook: Essential tools for working with data. "O'Reilly Media, Inc."
10. Zhang, C.W. and Wang, Y.B., 2010. Research on the application of distributed data mining in anti-money laundering monitoring system. In 2010 2nd International Conference on Advanced Computer Control, pp. 133-135). IEEE.
11. Han, J., Kamber, M. and Pei, J., 2012. Data Mining: concepts and techniques, 3rd Edn, Data Transformation by Normalization, Elsevier, ISBN 978-0-12-381479-1.
12. Paikari, E., 2023. Bug report quality prediction and the impact of including videos on the bug reporting process, University of California, Irvine.  https://escholarship.org/uc/item/9tn4t5gs [In Persian]
13. Boschetti, A. and Massaron, L., 2015. Python Data Science Essentials. Packt Publishing Ltd. 3rd Edn, Retrieved May 17, 2022, from    https://www.oreilly.com/library/view/python-data-science/9781789537864/
14. Mahmoudi, L., Razvian, M.T., Ghorchi, M. and Ostadtaghizadeh, A., 2020.Application of multilayer perceptron (MLP) neural network model in urban vulnerability zoning with emphasis on earthquake (a case study on municipal district 20 in Tehran), J. of Natural Environmental Hazards9(24), pp.129-150. http://doi.org/10.22111/JNEH.2020.31217.1551. [In Persian].
15. Nanda, S.R., Mahanty, B. and Tiwari, M.K., 2010. Clustering Indian stock market data for portfolio management. Expert Systems with Applications37(12), pp.8793-8798., 37(12),   https://doi.org/10.1016/j.eswa.2010.06.026
16. Abbasi, A. and Nikbakht, M., 2018. Identification and clustering outsourcing risks of aviation part-manufacturing projects in aviation industries organization using k-means method. J. of Modern Processes in Manufacturing and Production7(4), pp.1730.    https://civilica.com/doc/1146207/ [In Persian].
17. Soltani Nejad. D., 2015. Optimizing the investment portfolio using clustering methods: comprehensive humanities portal. J. of Asset Management and Financing. 4(4), pp.1-16. [In Persian].
18. Sayadi, M. and Omidi, M., 2020. Prediction-based portfolio optimization model for Iran’s oil-dependent stocks using data mining methods. Iranian Journal of Economic Studies, 8(1), pp.207-234.   https://doi.org/10.1016/j.jeconom.2019.04.017
19. Sadeghi Arani, Z. and Mohgar, A., 2019.Presenting a hybrid clustering model of Tehran Stock Exchange member companies: meta-heuristic algorithms approach. Farda Management Scientific Research Journal, 18(59), pp.18-3.    https://www.sid.ir/paper/386061/en [In Persian]
20. Abbasi, I., Dehekhani, H., Khozin, A. and Bazadeh, F., 2019. Designing a smart model for predicting financial wealth in insurance companies (data mining approach). J. of Investment Science, 9(34), pp.211-229.[In Persian].
21. Razin, A., 2015. Big buzz about big data: Five Ways Big Data Is Changing Finance, Forbes. https://www.forbes.com/sites/elyrazin/2015/12/03/big-buzz-about-big-data-5-ways-big-data-is-changing-finance/
22. Diebold, F. X., Ghysels, E., Mykland, P. and Zhang, L., 2019. Big data in dynamic predictive econometric modelling. J. of Econometrics, 212(1), pp.1-3. https://doi.org/10.1016/j.jeconom.2019.04.017
23. Majumdar, S. and Laha, A. K., 2020. Clustering and classification of time series using topological data analysis with applications to finance. Expert Systems with Applications, 162, pp.113868. https://doi.org/10.1016/j.eswa.2020.113868
24. Goodell, J. W., Kumar, S., Lim, W. M. and Pattnaik, D., 2021. Artificial intelligence and machine learning in finance: Identifying foundations, themes, and research clusters from bibliometric analysis. J. of Behavioral and Experimental Finance, 32, pp.100577.  https://doi.org/10.1016/j.jbef.2021.100577
25. Lai, M., 2022. Smart financial management system based on data mining and man-machine management. Wireless communications and mobile computing, 1, p.2717982.    https://doi.org/https://doi.org/10.1155/2022/2717982
26. Karami, A. and Moradi. M., 2006. Investigation of linear and non-linear relationships between financial ratios and stock returns in Tehran Stock Exchange. Accounting and Auditing Reviews. 3(2), pp.84-102.   https://doi.org/10.1108/eb043404
27. Namazi, M. and Rostami, N., 2006. The relationship between financial ratios and stock returns in Tehran Stock Exchange Market. The Accounting and Auditing Review13(44), pp.105-127.
28.Crammer, K. and Singer, Y., 2022. Support vector machines. Retrieved September 27, 2022, from   https://scikitlearn/stable/modules/svm.html
29. Jayanthi, M. K., 2009. Object oriented analysis and design of learning objects and applications of agent based reusable learning objects in e-Learning system design. Computer Science and Engineering: King Khalid University. https://www.researchgate.net/publication/344672573_Object_Oriented_Analysis_and_Design_of_Learning_Objects_Application_of_Agent_Based_Reusable_Learning_objects_in_e-Learning_System_Design
30. Ciano, T., 2024. Bitcoin price prediction and machine learning features: New financial scenarios, Reference Module in Social Sciences, Elsevier, ISBN 9780443157851, From https://doi.org/10.1016/B978-0-44-313776-1.00194-X.
31. Dudek, G., Fiszeder, P., Kobus, P. and Orzeszko, W., 2024. Forecasting cryptocurrencies volatility using statistical and machine learning methods: A comparative study, Applied Soft Computing, 151, pp.111132.    https://doi.org/10.1016/j.asoc.2023.111132.