Journals / İstanbul Ticaret Üniversitesi Sosyal Bilimler Dergisi / 2022 / Cilt: 21 Sayı: 43

USING MACHINE LEARNING ALGORITHMS TO GOING CONCERN ASSESSMENT: EVIDENCE FROM TURKEY

İŞLETMELERİN SÜREKLİLİĞİNİN DEĞERLENDİRİLMESİNDE MAKİNE ÖĞRENME ALGORİTMALARININ KULLANIMI: TÜRKİYE ÖRNEĞİ

Pages
111–132
Publication Date
2022-06-15
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Findings: As a result of the analysis, the overall success rates of decision tree and random forest algorithms were determined as 91.2% and 91.1%, Type 1 error 7.1% and 7.6%, Type 2 error 13.2% and 12.2%.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Purpose: The purpose of this study is the use of machine learning algorithms to evaluate the continuity of businesses.
📊
Key Findings & Data:For this purpose, the data derived from the 136 companies constantly listed in Borsa Istanbul between the years 2010-2019 are used.
💡
Conclusion & Impact:Findings: As a result of the analysis, the overall success rates of decision tree and random forest algorithms were determined as 91.2% and 91.1%, Type 1 error 7.1% and 7.6%, Type 2 error 13.2% and 12.2%.
🔬Design:Modeling & Simulation
📍Scope:2010-2019 Verileri
⚙️Variables:Süreklilik · Makine Öğrenme Algoritmaları · Borsa İstanbul

Abstract

Purpose: The purpose of this study is the use of machine learning algorithms to evaluate the continuity of businesses. For this purpose, the data derived from the 136 companies constantly listed in Borsa Istanbul between the years 2010-2019 are used. Companies whose data could not be accessed or with different taxonomy were not included in the study. Approach: Artificial neural networks, decision tree, support vector machines, random forest, k-nearest neighbor classification, logistic regression and gaussian naive bayes algorithms were used in the study. The artificial neural networks and support vector machines used in the study work as black boxes. Other algorithms used in the study are rule-based. Class balanced 10-fold cross validation method was used in the application of the methods. Findings: As a result of the analysis, the overall success rates of decision tree and random forest algorithms were determined as 91.2% and 91.1%, Type 1 error 7.1% and 7.6%, Type 2 error 13.2% and 12.2%. In addition, return on assets ratio, ratio of retained earnings to total assets, financial leverage ratio, ratio of cash flow amount to total liability and current ratio variables were determined as important variables to evaluate the continuity of businesses. Originality: Numerous methods have been used in the literature to evaluate the continuity of businesses. However, in recent years, machine learning has come to the fore. In Turkey, the number of studies conducted with machine algorithms in the evaluation of the continuity of businesses is very few. In this study, the most used algorithms were applied together. Thus, the most successful algorithms were determined.

Özet

Amaç: Bu çalışmanın amacı, işletmelerin sürekliliğinin değerlendirilmesi amacıyla makine öğrenme algoritmalarının kullanımıdır. Bunun için Borsa İstanbul’da 2010-2019 yılları arasında kesintisiz işlem gören 136 şirketin verileri kullanılmıştır. Çalışmaya verilerine ulaşılamayan veya taksonomisi farklı şirketler dahil edilmemiştir. Yaklaşım: Çalışmada yapay sinir ağları, karar ağacı, destek vektör makineleri, rassal orman, k-en yakın komşular sınıflandırma, lojistik regresyon ve gaussian naive bayes algoritmaları kullanılmıştır. Çalışmada kullanılan yapay sinir ağları ile destek vektör makineleri kara kutu olarak çalışmaktadır. Çalışmada kullanılan diğerler algoritmalar kural bazlıdır. Yöntemlerin uygulamasında sınıf dengeli 10 kat çapraz doğrulama yöntemi kullanılmıştır. Bulgular: Yapılan analiz sonucunda karar ağacı ve rassal orman algoritmalarının genel başarı oranları %91,2 ve %91,1, Tip 1 hatası %7,1 ve %7,6, Tip 2 hatası ise %13,2 ve %12,2 olarak tespit edilmiştir. Ayrıca, süreklilik değerlendirmesinde aktif karlılık oranı, birikmiş karlar/toplam aktif oranı, finansal kaldıraç oranı, nakit akış tutarının toplam yükümlülük içindeki oranı ile cari oran önemli değişkenler olarak belirlenmiştir. Özgünlük: Literatürde işletmelerin sürekliliğinin değerlendirilmesine yönelik çok sayıda yöntem kullanılmıştır. Ancak son yıllarda makine öğrenmeleri ön plana çıkmaktadır. Türkiye’de ise işletmelerin sürekliliğinin değerlendirilmesinde makine algoritmalarıyla yapılan çalışma sayısı çok azdır. Bu çalışmada en çok kullanılan algoritmalar birlikte uygulanmıştır. Böylelikle en başarılı algoritmalar tespit edilmiştir.

🔖

Cite This Article

TERZİ, S. (2022). USING MACHINE LEARNING ALGORITHMS TO GOING CONCERN ASSESSMENT: EVIDENCE FROM TURKEY. İstanbul Ticaret Üniversitesi Sosyal Bilimler Dergisi, Cilt: 21 Sayı: 43, 111–132. https://ajindex.com/articles/907016

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (11)

  1. Altman, Edward 1. & McGough, Thomas P. (1974). Evaluation of a company as a going concern. Journal of Accounting, Auditing and Finance, 6(4), 4-19.
  2. Bell, Timothy B. & Tablo, Richard H. (1991). Empirical analysis of audit uncertainty qualifications. Journal of Accounting Research, 29(2), 350-370. https://doi.org/10.2307/2491053
  3. Bellovary, Jodi L., Giacomino, Don E. & Akers, Michael D. (2007). A review of going concern prediction studies: 1976 to present. Journal of Business & Economics Research, 5, 9-28. https://doi.org/10.19030/jber.v5i5.2541
  4. Carey, Peter J., Geiger, Marshall A. & O’Connell, Brendan T. (2008). Costs associated with going-concern-modified audit opinions: an analysis of the Australian audit market. Abacus, 44(1), 61-81. https://doi.org/10.1111/j.1467-6281.2007.00249.x
  5. Carson, Elizabeth, Fargher, Neil L., Geiger, Marshall A., Lennox, Clive S., Raghunandan, K. & Willekens, Marleen (2013). Audit reporting for going-concern uncertainty: a research synthesis. Auditing: A Journal of Practice & Theory, 32(1), 353-384. https://doi.org/10.2308/ajpt-50324
  6. Chen, Kevin C. W. & Church, Bryan K. (1992). Default on debt obligations and the issuance of going-concern opinions. Auditing: A Journal of Practice and Theory, 11(2), 30–50.
  7. Gallizo, José Luis & Saladrigues, Ramon (2016). An analysis of determinants of going concern audit opinion: Evidence from Spain stock Exchange, Intangible Capital, 12(1), 1-16. http://dx.doi.org/10.3926/ic.683
  8. Geiger, Marshall A. & Raghunandan, K. (2002). Going-concern opinions in the ‘new’ legal environment. Accounting Horizons, 16(1), 17-26. https://doi.org/10.2308/acch.2002.16.1.17
  9. Goodman, Barbara, Braunstein, Daniel N., Reinstein, Alan & Gregory, W. George (1995). Explaining auditors going concern decisions: assessing managements capability. Journal of Applied Business Research, 11(3), 82-93. https://doi.org/10.19030/jabr.v11i3.5863
  10. Haron, Hasnah, Hartadi, Bambang, Ansari, Mahfooz & Ismail, Ishak (2009). Factors influencing auditors' going concern opinion. Asian Academy of Management Journal, 14(1), 1-19.
  11. Harris, Carolyn K. & Harris, William T. (1990, April). An expert decision support system for auditor `going concern' evaluations. Poster session presented at the Symposium on Applied Computing, Arkansas. Koh, Hian C. & Killough, Larry N. (1990). The use of multiple discrıminant analysis in the assessment of the going-concern status of an audit client. Journal of Business Finance & Accounting, 17(2), 179-192. https://doi.or