بررسی توان شیوه‌های داده کاوی در تفکیک شرکت‌های درمانده و غیر درمانده

نوع مقاله : مقاله پژوهشی

نویسندگان

1 استادیار، گروه حسابداری، واحد اراک، دانشگاه آزاد اسلامی، اراک، ایران

2 کارشناسی ارشد حسابداری، گروه حسابداری، واحد اراک، دانشگاه آزاد اسلامی، اراک، ایران.

3 دانشجوی دکتری حسابداری، گروه حسابداری، واحد کاشان، دانشگاه آزاد اسلامی، کاشان، ایران.

چکیده

درماندگی مالی یکی از موضوعات مهم در بازارهای مالی بوده و می­تواند در مدل تصمیم­گیری سرمایه‌گذاران وارد شود تا بتوانند به تجزیه و تحلیل وضعیت مالی موارد سرمایه­گذاری پرداخته و با مشخص‌شدن سطح درماندگی مالی، با اطمینان در موقعیت مناسب تصمیم­گیری کنند؛ بنابراین در این پژوهش بررسی می‌شود که آیا می‌توان یک رویکرد محاسباتی نوین برای پیش‌بینی درماندگی مالی، با استفاده از شیوه­های خوشه­بندی و طبقه­بندی ارائه کرد؟ جامعه آماری پژوهش، شرکت­های پذیرفته‌شده در بورس اوراق­بهادار تهران در سال­های 1393 الی 1399 می­باشد؛ که با استفاده از روش حدف سیستماتیک؛ اطلاعات 123 شرکت استخراج گردید؛ برای پاسخ‌گویی به سؤالات پژوهش از 6 علامت هشدار­دهنده درماندگی مالی به همراه شیوه‌های داده‌کاوی تحلیل مؤلفه‌های اساسی و خوشه‌بندی، برای تعیین شرکت‌های درمانده مالی استفاده شد؛ سپس به‌منظور ارائة مدلی برای پیش‌بینی درماندگی مالی، از 23 متغیر مالی و غیرمالی (که در نهایت تعداد 13 متغیر به عنوان ورودی به علت داشتن ضریب همبستگی بالا با متغیر در ماندگی مالی انتخاب شدند) به همراه شیوه‌ درخت تصمیم استفاده شد. یافته‌های پژوهش بیانگر این موضوع هستند که شیوه­های داده کاوی امکان تفکیک شرکت‌های درمانده و غیر‌درمانده را فراهم می­کند و بیانگر یک روش تحلیلی خودکار برای کشف درماندگی بالقوه می‌باشد.

کلیدواژه‌ها


عنوان مقاله [English]

Examining the power of data mining methods in separating helpless and non-helpless companies

نویسندگان [English]

  • Ali Laalbar 1
  • Mohadeseh Salmani 2
  • Elham Darajati 3
1 Assistant prof., Department of Accounting, Arak branch, Islamic Azad University, Arak, Iran.
2 Department of Accounting, Arak branch, Islamic Azad University, Arak, Iran.
3 Ph.D. Candidate in Accounting, Islamic Azad University, Kashan branch, Kashan, Iran.
چکیده [English]

Behavioral finance explains contradictory patterns with market efficiency hypotheses with behavioral biases. One of the most common price patterns in the stock market is the pattern of momentum, which can be driven by investors' adjustment and anchoring bias and disposition effect. In this study, the role of adjustment and anchoring bias and disposition effect on the formation of momentum returns on the Tehran Stock Exchange are examined. Using the portfolio study method and the data of the research period of 2007-2016, it was found that investors are more affected by adjustment and anchoring bias compared to disposition effect and form a pattern of momentum by reversing against the maximum price thresholds with a one-year period as the reference price. Also, among the maximum thresholds, investors are most affected by the maximum price of 26 weeks with a six-month waiting period, and further analysis and analysis using the Fama-Macbeth regression and the Fama-French three-factor model confirm these results.

کلیدواژه‌ها [English]

  • Financial information
  • Non-financial information
  • Financial helplessness
  1. Acosta-González, E., & Fernández-Rodríguez, F, Ganga H. (2017). Predicting Corporate Financial Failure Using Macroeconomic Variables and Accounting Data, Computational Economics53, 227-257.
  2. Adeli, Omid Ali; Sephovand, Zahra. (2018). Study on the identification and prioritization of factors affecting bank bankruptcy, the fourth national conference on management, accounting and economics with an emphasis on regional and global marketing, Tehran: Shahid Beheshti University, permanent secretariat of the conference. ،https://civilica.com/doc/915178. (In Persian).
  3. Ahmadpour, A., Shahsavari, M., & amoozad Khalili, A. (2016). Investigation of Important Factors on Risk of Financial Bankruptcy. Empirical Studies in Financial Accounting13(51), 9-34. (In Persian).
  4. Aliakbarlou, A., Mansourfar, G., & Ghayour, F. (2020). Comparing the Identifying Criteria for Financially Distressed Companies using Logistic Regression and Artificial Intelligence Methods. ـJournal of Financial Management Perspective10 (29), 147-166.(In Persian).
  5. Altman, E. Iwanicz-Drozdowska, M., Laitinen, E.K., and Suvas, A. (2017). Financial Distress Prediction in an International Context: A Review and Empirical Analysis of Altman's Z-Score Model. Journal of International Financial management and Accounting, 28 (2) pp. 131-171.
  6. Azizi, S., & Jokar, H. (2022). The Effect of Working Capital Information in Predicting Financial Distress Based on Combination of Artificial Neural Network and Particle Swarm Optimization Algorithm. ـJournal of Financial Management Perspective, (12( 38, -. doi: 10.52547/jfmp.2022.224059.111. (In Persian).
  7. Botshekan, M., Salimi, M., & Falahatgar Mottahedjoo, S. (2018). Developing a hybrid approach for financial distress prediction of listed companies in Tehran stock exchange. Financial Research Journal20(2), 173-192. doi: 10.22059/frj.2018.248070.1006570. (In Persian).
  8. Chiaramontea, L, Casu, B. (2018). Capital and liquidity ratios and financial distress. Evidence from the European banking industry, The British Accounting Review, 9(2), 138-161.
  9. Darabi, Roya, & Salmanian, Maryam. (2016). Analytical review of financial helplessness. Accounting and auditing studies6(23), 47-64. (In Persian).
  10. Ebrahimi sarv olia, M., Babajani, J., akhond, M., & fakher, E. (2019). A Pattern for Dynamic Prediction of Financial Distress by Using Survival Analysis. Quarterly Journal of Quantitative Economics) .15(4), 167-198. (In Persian).
  11. Ghaffari, Zahra. (2019). Investigating the relationship between systematic risk, economic uncertainty and corporate bankruptcy, master's thesis, Saveh Azad University. (In Persian).
  12. Hernandez, M.T. & N. Wilson. (2017). Financial Distress and Bankruptcy Prediction Among Listed Companies Using Accounting, Market and Macroeconomic Veriables, International Review of Final Analysis, In Press, Available online 26 February.
  13. Hosseini, S., Oladi, J., & Amirnejad, H. (2016). The Priority of Criteria and Indicator of the Evaluation of National Parks Using Entropy and Likert Techniques., Natural Ecosystems of Iran, 7(3), 83-97. (In Persian).
  14. Khodakarimi, P., & Piri, P. (2017). Predicting Financial Distress with using combined model of Accounting and Market Data with Logistic Regression Approach. Empirical Studies in Financial Accounting, 14(55), 145-168. (In Persian).
  15. Liang, D. & Tsai, C. f. & Wu, H. T. (2019). The effect of feature selection on financial distress prediction. Journal of Knowledge-Based Systems, 73 (1): 289-297.
  16. Najarpoor, Mahsa; khanlari, morteza. (2019). Predicting financial helplessness in companies listed on the Tehran Stock Exchange with emphasis on accruals and cash flows, Journal of accounting and management vision, 3 (24), 94-107. (In Persian). 
  17. Namazi, Mohammad, & Kermani, Ehsan. (2009). Investigating the Effects of Ownership Structure on The Performance of the Companies Accepted in the Tehran Stock Exchange. Accounting and Auditing Review15(4), 53. (In Persian). 
  18. Rasoul Tahmasebi, Ali Asghar Anvary Rostamy, Abbas Khorshidi, Seyyed Jalal Sadeghi Sharif, (2018). Predicting financial distress risk of firms listed in Tehran Stock Exchange using factor analysis, decision tree and logistic regression models, Journal of Investment Knowledge, 7(27), 189-206. magiran.com/p1891399. (In Persian).
  19. Velia Gabriella, Cenciarelli, Giulio, Greco, Marco, Allegrini. (2018). “Does intellectual capital help predict bankruptcy?”, Journal of Intellectual Capital, 19 (­2), 321-337.
  20. Vaghfi, S. H., Javanshiri, H., Eskandari, A., & Nourbakhsh Hosseiny, Z. (2022). Content analysis of financial distress.Accounting and Auditing Studies, 11(41), 65-84. doi: 10.22034/iaas.2022.149715. (In Persian).
  21. Wang, Y. (2022). Financial crisis prediction model of listed companies based on statistics and AI.Scientific Programming, 2022.
  22. Zhehao, Jia, Yukun ,Shi, Cheng Yan & Meryem, Duygun. (2020). Bankruptcy prediction with financial systemic risk, The European Journal of Finance, 26(2), 7-8.
  23. https://blog.faradars.org/confusion-matrix-from-zero-to-hero/