توانایی ماشین بردار پشتیبان در پیش بینی احیای مالی

هارونکلایی, ;کاظم; نبوی چاشمی, سیدعلی; برزگر, قدرت اله; داداشی, ایمان

doi:10.22051/jfm.2023.35495.2532

توانایی ماشین بردار پشتیبان در پیش بینی احیای مالی

نوع مقاله : مقاله پژوهشی

نویسندگان

¹ دانشجوی دکتری حسابداری، واحد بابل، دانشگاه آزاد اسلامی، بابل، ایران

² دانشیارمدیریت، دانشکده مدیریت، دانشگاه آزاد اسلامی، بابل، ایران

³ استادیار گروه حسابداری، دانشکده علوم اقتصادی و اداری دانشگاه مازندران، بابلسر، ایران

⁴ استادیار حسابداری، دانشکده علوم اقتصادی و اداری، دانشگاه قم، قم، ایران

10.22051/jfm.2023.35495.2532

چکیده

چکیده
یکی از مهمترین موضوعات حوزه مدیریت مالی، آن است که سرمایه‌گذاران بتوانند فرصت‌های مطلوب سرمایه‌گذاری را از فرصت‌های نامطلوب تشخیص دهند. یکی از راهکارهای کمک به سرمایه‌گذاران پیش‌بینی احیای مالی (خروج از درماندگی) شرکت‌های دارای درماندگی مالی است. از این رو، این پژوهش در صدد است مدلی جهت پیش‌بینی احیای مالی با استفاده از الگوریتم ماشین بردار پشتیبان برای شرکت‌های پذیرفته شده در بورس اوراق بهادار تهران ارائه نماید. برای دستیابی به این هدف،54 متغیر مالی با استفاده از الگوریتم‌ انتخاب ویژگی لارس تعیین گردید و برای آزمون دقت نتایج مدل پیشنهادی از الگوریتم‌ یادگیر ماشین بردار پشتیبان استفاده شده است. بدین منظور در دوره زمانی 1380 تا1397 اطلاعات 167 شرکت درمانده‌ای که از درماندگی مالی خارج و احیا شده‌اند، استخراج گردید. یافته‌های پژوهش نشان می‌دهد، مدل تحقیق با دقت 74% زمان احیا و خروج شرکت درمانده مالی را از درماندگی مالی به درستی پیش بینی می‌نماید.
طبقه‌بندی موضوعی: G40 ، C15.

کلیدواژه‌ها

20.1001.1.23453214.1402.11.1.7.3

عنوان مقاله [English]

The Ability of Support Vector Machine (SVM) in Financial Recoverey Prediction

نویسندگان [English]

Kazem Haronkolaee ¹
SeyyedAli Nabavichshmi ²
Ghodratalah Barzegar ³
Iman Dadashi ⁴

¹ PhD student in accounting, Babol branch, Islamic Azad University, Babol, Iran

² Associate Professor of Management, Faculty of Management, Islamic Azad University, Babol, Iran

³ Assistant Professor of Accounting, Department of Accounting, Faculty of Economic and Administrative Sciences, University of Mazandaran

⁴ Assistant Professor of Accounting, Faculty of Economic and Administrative Sciences, University of Qom, Qom, Iran

چکیده [English]

One of the most important issues in the field of financial management is that investors can distinguish favorable investment opportunities from unfavorable ones. One way to help investors is to anticipate the financial recovery (exit from helplessness) of companies with financial distress. Therefore, this study intends to provide a model for predicting financial recovery using the support vector machine algorithm for companies listed on the Tehran Stock Exchange. To achieve this goal, 54 financial variables were determined using the Lars feature selection algorithm and to test the accuracy of the results of the proposed model, the support vector learning algorithm was used. For this purpose, in the period of 2001-2018, the information of 167 helpless companies that were out of financial helplessness and revived was extracted. The research findings show that the research model accurately predicts the recovery time of the financially helpless company from financial distress with 74% accuracy.

کلیدواژه‌ها [English]

Financial Distress
Lars Algorithm
Support Vector Machine Algorithm

مراجع

Barboza, F., Kimura, H., & Altman, E. (2017), “Machine learning models and bankruptcy prediction”, Expert Systems with Applications, 83(2), 405-417.

Bibeault, D.B. (1998) Corporate Turnaround: How Managers Turn Losers into Winners, Washington, DC, Beard Books.

Binti, S & Ameer, R. (2010). Turnaround prediction of distressed companies: evidence from Malaysia. Journal of Financial Reporting and Accounting, 8(2), 143-159.

Botshekan, M. Salimi, M & Falahatgar, S. (2018). Developing a hybrid approach for financial distress prediction of listed companies in Tehran stock. Financial Research, 20(2), 173-192. (In Persian)

Chenchehene, j& Mensah, k. (2014). Corporate Survival: Analysis of Financial Distress and Corporate Turnaround of the UK Retail Industry. International Journal of Liberal Arts and Social Science: 2 (9), 18-34.

Chu-kuo Chin. (2016). Predicting corporate turnaround of listed companies in South Africa. Journal of Management, 19(2), 13-36.

Efron, B. Hastie, T. Johnstone, I. & Tibshirani, R. (2004). Least Angle Regresion. The Annals of Statistics, 32(2), 407–499.

Eunice, K & Maina, S. (2019). Turnaround Strategies and Performance of Dairy Companies. International Journal of Businness & Management, 7 (6): 284-294

Fallahpour, S. Raei, R. & Norouzian Lakvan, E. (2018). Applying Combined Approach of Sequential Floating Forward Selection and Support Vector Machine to Predict Financial Distress. Financial Research Journal, 20(3), 289-304. (In Persian)

Filatotchev, I. & Toms, S. (2006). Corporate Governance and Financial Constraints on Strategic Turnarounds. Journal of Management Studies, 43 (3): 407-433.

Fu, J. Yu, Y. Maulin, H. Chai, J. & Chang Chen, C. (2014). Feature extraction and pattern classification of colorectal polyps in colonoscopic imaging. Computerized medical imaging and graphics, 38 (4), 75-267.

Ghazanfari, M. Rahimi, A & Askari, A. (2018). predict the bankruptcy of domestic companies Based on Intelligent System. Financial Accounting and Auditing Research, 10(37), 159-193. (In Persian)

Ghazzawi, I. (2018). Organizational Turnaround: A Conceptual Framework and Research Agenda. American Journal of Management, 17(7), 10-24.

Kordestani, G & Tatli, R. (2013). Evaluating the predictive power of bankruptcy models. Journal of Audit Science, 14(55), 51-70. (In Persian)

Mehrani, S., kamyabi, Y., & ghayour, F. (2020). Effects of Accounting and Non-Accounting Indices on Financial Distress Prediction: Comparing Parametric and Non-parametric Methods. Empirical Research in Accounting, 9(4), 49-72. (In Persian)

Rahman Seresht, H. Hasas Yeganeh. Y. Falah, M & Irandoost, M. A Strategic Model of in Crisis Firm Turnaround Process. (2013). Business Management, 6(3), 497-516. (In Persian)

Ramooz, N & Mahmoudi, M. (2017). The Prediction of the Risk of Financial Bankruptcy Using Hybrid Model in Tehran Stock Exchange. financial management strategy, 5(16), 51-57. (In Persian)

Situm, M. (2015). Recovery from distress and insolvency: A comparative analysis using accounting ratios. Proceedings of the 6th Global Conference on Managing in Recovering Markets, GCMRM 2015, 589-606.

Slatter, S. (1984). Corporate recovery: Successful turnaround strategies and their implementation. Singapore: Penguin Books.

Soufi, M. Homayonfar, M & Fadaei, M. (2020). Developing an Optimal Method for Financial Distress Prediction of the Firm. Investment Knowledge, 9(35), 85-100. (In Persian)

Tenkasi, R & Kamel, Y. (2016). To Bankruptcy and Back: Turnaround Strategies for Firm Emergence, long _ Term Survival, and Speed. In Researich in Oraganizational Change and Development. Emerald Group Publishing Limited, 221-259.

vaghfi, S. H. (2019). Using artificial intelligence algorithm in Financial Bankruptcy by Macro-economic and Accounting variables in listed companies for stock exchange in Tehran. Journal of Decisions and Operations Research, 4(2), 158-173. (In Persian)

Vapnik, V. N. (1995). The Nature of Statistical Learning Theory. Springer Verlag New York.