نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه مدیریت مالی، واحد اسفراین، دانشگاه آزاد اسلامی، اسفراین، ایران.

2 گروه مهندسی صنایع، مجتمع آموزش عالی فنی و مهندسی اسفراین، اسفراین، ایران.

10.22105/dmor.2023.340413.1604

چکیده

هدف: اخراج شرکت‌­ها با وجود اهمیت در مسایل اقتصادی و اجتماعی جامعه، کم‌تر در ادبیات مالی مورد‌‌توجه قرار گرفته است. این موضوع از آن جهت دارای اهمیت است که برای هر کشور، یکی از معیارهای سنجش اقتصادی، حجم بازار سرمایه می‌­باشد؛ بنابراین اخراج شرکت‌­ها نه‌تنها باعث از بین رفتن اعتبار شرکت، قیمت سهام و بازار فروش سهام آن شرکت می‌شود بلکه بر رشد بازار و اقتصاد هر کشور نیز موثر است. پژوهش حاضر به دنبال بررسی صورت­‌های مالی و گزارش حسابرسی شرکت‌های فعال و مقایسه آن با شرکت‌های لغو‌پذیرش‌شده می‌باشد تا به کمک فنون مدل‌سازی هوش مصنوعی، مدلی را برای پیش‌بینی شرکت‌های لغوپذیرش‌شده در بورس اوراق بهادار تهران طراحی نماید.
روش‌شناسی پژوهش: در این پژوهش که روی شرکت‌های بورس اوراق بهادار تهران انجام پذیرفته است، داده­‌های مربوط به سه سال قبل از اخراج 73 شرکت حذف‌شده از بورس از سال 1382 تا سال 1397 در گروه اول و داده‌های 148 شرکت فعال که به‌صورت مستمر در بورس حضور داشتند در گروه دوم و با روش حذفی سیستماتیک انتخاب گردیدند. سپس با تکنیک‌های داده‌کاوی که از کارآمدترین و به‌روزترین مدل‌های هوش مصنوعی هستند و به کمک طبقه‌بند­های شبکه عصبی پرسپترون چندلایه، درخت تصمیم، و طبقه‌بند نظریه بیز به پیش‌بینی شرکت‌های لغو‌پذیرش‌شده از بورس پرداخته شده است.
یافته‌ها: یافته‌ها نشان می‌دهد بهترین عملکرد را طبقه‌بند بیز داشته است و شبکه عصبی پرسپترون چندلایه در جایگاه دوم و طبقه‌بند درخت تصمیم در جایگاه سوم قرار گرفته است.
اصالت/ارزش افزوده علمی: پژوهش­‌های کمی در حوزه پیش‌بینی اخراج شرکت­‌ها از بازار سرمایه در ایران شده است. این پژوهش با پر کردن این گپ، به پژوهشگران پیشنهاد داده است با استفاده از سایر طبقه‌بند‌ها، ترکیب کردن چندین طبقه‌بند با یکدیگر به‌منظور پوشش بهتر خطاهای هر یک، ترکیب کردن طبقه‌بند­ها با یکدیگر و وزن‌دهی به روشی که دقت بالاتری داشته باشد، اضافه کردن سایر متغیرهای تاثیرگذار در اخراج شرکت­‌ها از جمله ساختار مالکیت و ترکیب سهام‌داران می­تواند نتایج دیگری به دست آید.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Predicting the delisted companies of Tehran Stock Exchange using machine learning based algorithms

نویسندگان [English]

  • Aminollah Zarghami 1
  • Meysam Doaei 1
  • Abtin Boostani 2

1 Department of Financial Management, Esfarayen Branch, Islamic Azad University, Esfarayen, Iran.

2 Department of Industrial Engineering, Technical and Engineering Higher Education Complex Esfarayen, Esfarayen, Iran.

چکیده [English]

Purpose: Delisted companies, despite their importance in the economic and social issues of society, is less considered in the financial literature. This issue is important because for each country, one of the criteria for economic measurement is the size of the capital market. Therefore, the delisted companies not only destroys the company's reputation, its stock price and the market for the sale of its shares, but also affects the growth of the market and the economy of each country. The present study seeks to review the financial statements and audit reports of active companies and compare it with delisted companies to design a model for forecasting delisted companies in the Tehran Stock Exchange with the help of artificial intelligence modeling techniques.
Methodology: In this study, which was conducted on companies of the Tehran Stock Exchange, data related to three years before the delisting of 73 companies removed from the stock exchange from 2003 to 2019 in the first group and data of 148 active companies that are continuously. They were present in the stock market in the second group and were selected by systematic elimination method. Then, with data mining techniques, which are among the most efficient and up-to-date models of artificial intelligence, and with the help of multi-layered perceptron neural network classifiers, decision tree, and Bayesian theory classifiers, stock delisted companies have been predicted.
Findings: The findings show that the Bayesian classifier had the best performance and the multilayer perceptron neural network was in the second place and the decision tree classifier was in the third place.
Originality/Value: Little research has been done in the field of predicting delisted companies from the Iran capital market. This study by filling this gap, suggests to researchers to use other classifiers, combine several classifiers together to better cover the errors of each, combine classifiers with each other and weigh in a way that is more accurate, add other variables influential in the dismissal of companies, including the ownership structure and shareholder composition can have other results.

کلیدواژه‌ها [English]

  • Delisted of stock exchange
  • Multi-layer perceptron neural network
  • Decision tree
  • Bayesian theory
  • Artificial intelligence
  1. Altman, E. I., & Saunders, A. (1997). Credit risk measurement: developments over the last 20 years. Journal of banking & finance21(11-12), 1721-1742.
  2. Asdolahi, M. (2014). The ability of independent auditor's opinion type and cash flow report in bankruptcy forecasting(Master Thesis, Islamic Azad University of Shahrood). (In Persian). https://www.jamv.ir/article_152806.html
  3. Dabagh, R., & Sheikhbeiglou, S. (2021). Bankruptcy prediction of listed companies in Tehran’s Stock Exchange by artificial neural network (ANN) and fulmer model. Journal of development and capital5(2), 153-168. (In Persian). https://jdc.uk.ac.ir/article_2841_fbcef964f0016ae661f54e4b384a57f5.pdf?lang=en
  4. Daneshvar, L. (2016). Investigating the effect of financial ratios and auditor's report on predicting the bankruptcy of companies listed on the Tehran Stock Exchange (Master Thesis, Islamic Azad University of Zanjan). (In Persian). https://ganj.irandoc.ac.ir/#/articles/14b42b3d16509fad1d47e1a430506655
  5. Darvishinia, R., Ebrahimzadeh Shermeh, H., & Barzkar, S. (2019). Development of a forecasting model for investment in Tehran Stock Exchange based on seasonal coefficient. Journal of applied research on industrial engineering6(4), 333-366. (In Persian). https://doi.org/10.22105/jarie.2019.196392.1103
  6. Doaei, M., & Saberfard, M. (2021). A chance constrained recourse approach for the portfolio selection problem in Iran capital market. Financial engineering and portfolio management12(46), 667-690. (In Persian). https://dorl.net/dor/20.1001.1.22519165.1400.12.46.29.5
  7. Doaei, M., Mirzaei, S. A., & Rafigh, M. (2021). Hybrid multilayer perceptron neural network with grey wolf optimization for predicting stock market index. Advances in mathematical finance and applications6(4), 883-894.
  8. Fakhrehosseini, S. F., & Aghaei Meybodi, O. (2019). Prediction and identification of companies with high bankruptcy probability in Tehran Stock Exchange (different analysis of models). Journal of decisions and operations research4(2), 100-111. (In Persian). https://doi.org/10.22105/dmor.2019.179504.1111
  9. Ghadiri Moghadam, A., Gholampour Fard, M. M., & Nasir Zadeh, F. (2010). Investigating the ability of Altman and Ehlson's bankruptcy prediction models in predicting the bankruptcy of companies admitted to the stock exchange. Monetary & financial economics16(28), 193-220. (In Persian). https://doi.org/10.22067/pm.v16i28.2739
  10. Ghasemiyeh, R., Moghdani, R., & Sana, S. S. (2017). A hybrid artificial neural network with metaheuristic algorithms for predicting stock price. Cybernetics and systems48(4), 365-392.
  11. Ghorbani, B., Hoseini Ghoncheh, S. J., & Mohammadiler, Z. (2017). The effect of disclosure of strategic, non-financial and financial information on earnings management. Financial accounting and auditing research, 9(35), 23-40. (In Persian). https://www.sid.ir/fileserver/jf/6003913963502.pdf
  12. Hijazi, R., Rahmani, A., & Mozafari, Z. (2010). Investigating the effect of disclosure regulations on the quality of published information by Tehran Stock Exchange (TSE). Journal of securities exchange, 3(10), 23-36. (In Persian). https://www.magiran.com/paper/920216
  13. Hosseini, S. M., & Rashidi, Z. (2013). Bankruptcy prediction of companies listed corporations in Tehran Stock Exchange by using decision tree and logistic regression. Financial accounting research5(3), 105-128. (In Persian). https://dorl.net/dor/20.1001.1.23223405.1392.5.3.9.6
  14. Pour, E. K., & Lasfer, M. (2013). Why do companies delist voluntarily from the stock market? Journal of banking & finance37(12), 4850-4860.
  15. Khajavi, S., & Momtazian, A. (2014). Investigation the quality of financial information disclosure effect on current and future stock return of listed companies of Tehran Stock Exchange. Financial accounting knowledge1(1), 9-27. (In Persian). https://jfak.journals.ikiu.ac.ir/article_1219_859caad6915bd9bfd4cc0a362778252d.pdf
  16. Khaje Nasiri, E. (2013). Effect of ownership structure, concentration and composition on the quality of disclosure(Master Thesis, University of Sistan and Baluchistan). (In Persian). https://www.virascience.com/thesis/658134/
  17. Mashhadi Ghareh Ghieih, H. (2011). Investigating the determinants of the auditor's opinion regarding the continuity of activity in companies listed on the Tehran Stock Exchange (Master Thesis, Islamic Azad University of Tehran). https://www.virascience.com/thesis/531514/
  18. Mazhari, S. M., Fereidunian, A. R., & Lesani, H. (2013). Bankruptcy prediction of the electrical firms within Iranian electricity exchange: empirical evidence from Tehran Stock Exchange. Computational intelligence in electrical engineering4(1), 9-24. (In Persian). https://isee.ui.ac.ir/article_15355_875855393faf8f09db1dfda50ebe332f.pdf
  19. Mirali, M. (2017). The role of stock market efficiency in the quality of companies' profits(Doctoral Dissertation, Islamic Azad University of Shahryar). (In Persian). https://jik.srbiau.ac.ir/article_20376_43733113a9dcdace68461ddcf3f4bf67.pdf?lang=en
  20. Mostafaei Darmian, S., & Doaei, M. (2022). Optimization of stock portfolio selection in Iran capital market using meta-heuristic algorithms. Quarterly journal of applied theories of economics8(4), 253-284.
  21. Muñoz-Izquierdo, N., Segovia-Vargas, M. J., & Pascual-Ezama, D. (2019). Explaining the causes of business failure using audit report disclosures. Journal of business research98, 403-414. https://doi.org/10.1016/j.jbusres.2018.07.024
  22. Nasirnia, M. (2013). Comparison of the ability of stochastic model with Ohlson and Altman models in predicting the suspension of activities of companies listed on the Tehran Stock Exchange(Master Thesis, Islamic Azad University of Tehran). (In Persian). https://ganj.irandoc.ac.ir//#/articles/bf9d462398a256761c4a5eb77691e1b4
  23. Nazemi, A., Momtazian, A., & Behpur, S. (2016). Investigating the relationship between disclosure quality and stock return of the companies listed in Tehran Stock Exchange: using a simultaneous equations system. Journal of accounting advances7(2), 219-244. (In Persian). https://ijfma.srbiau.ac.ir/article_17023_9fc20fe72ef4c8628db07d4f6c1d416c.pdf
  24. Peykani, P., Nouri, M., Eshghi, F., Khamechian, M., & Farrokhi-Asl, H. (2021). A novel mathematical approach for fuzzy multi-period multi-objective portfolio optimization problem under uncertain environment and practical constraints. Journal of fuzzy extension and applications2(3), 191-203. (In Persian). https://doi.org/10.22105/jfea.2021.287429.1150
  25. Rahbar, M. A. (2022). Evaluation of the hybrid method of genetic algorithm and adaptive neural-fuzzy network (ANFIS) model in predicting the bankruptcy of companies listed on the Tehran Stock Exchange. Journal of applied research on industrial engineering9(3), 274-290.
  26. Rasouli Ghahroudi, M., & Fakhraei, E. (2017). The impact of capital structure and ownership structure on the survival of companies in Tehran Stock Exchange market. Planning and budgeting22(1), 73-101. (In Persian). http://jpbud.ir/files/site1/user_files_e54c2e/rasouli-A-10-1158-2-9149ac0.pdf
  27. Setayesh, M. H., & Kazemnejad, M. (2012). Effective factors on disclosure quality of the firms listed in Tehran Stock Exchange. Journal of accounting advances, 4(1), 49-79. (In Persian). https://jaa.shirazu.ac.ir/article_514_dac76f2e26d27df3817a4ed14d8a9a32.pdf
  28. Shah Jooghi, J. (2014). Investigating the relationship between information disclosure rating and financial distress in Tehran Stock Exchange companies(Master Thesis, Islamic Azad University of Shahrood). (In Persian). https://ganj.irandoc.ac.ir/#/articles/1f5f9f099c8e6d6c5b039fdde6c9848f
  29. Vadiei, M. H., Samaei Rahni, S., & Choupani, M. R. (2017). Evaluation and comparison of the auditor's report of active and canceled companies admitted to the Tehran Stock Exchange. Audit science, 17(66), 131-150. (In Persian). https://danesh.dmk.ir/article-1-1495-fa.pdf
  30. Vakilifard, H, Pilehvari, N., & Zeidi, S. S. (2014). Presenting a model for predicting the bankruptcy of companies listed on the Tehran Stock Exchange using the adaptive neural fuzzy inference system (ANFIS). Financial engineering and securities management, 5(18), 17-30. (In Persian). https://dorl.net/dor/20.1001.1.22519165.1393.5.18.2.3
  31. Zamanian, G., Sheyhaki Tash, M., & Niknejad, M. (2014). Measuring likelihood coefficient of bankruptcy for companies listed in Tehran Stock Exchange (application of ohlson model). Public management researches6(22), 71-85. (In Persian). https://jmr.usb.ac.ir/article_1589_416806077f161d680a2e247832f2c7e6.pdf
  32. Zare, S. (2017). Presenting bankruptcy prediction model with fuzzy neural network approach in stock exchange (Master Thesis, Yazd University). https://ganj.irandoc.ac.ir/#/articles/26ccbbef955fdf927f0eb10c6f0dfe56