Predicting Financial Failure: Empirical Evidence from Publicly – Quoted Firms in Developed and Developing Countries

Abstract

This paper analyzes the data of 570 firms from developed and developing countries between 2010 and 2019 in an attempt to create high–accuracy financial failure prediction models. In this sense, we utilize three different methods, namely logistic regression (LR), artificial neural networks (ANN), and decision trees (DT), and compare the classification accuracy performances of these techniques. Using 16 financial ratios as independent variables, ANN is able to generate the most accurate prediction and outperforms the other methods in predicting failure. Otherwise said, ANN yields a correct classification accuracy of 98.1% one year prior to failure while LR and DT achieve accuracy rates of 94.7% and 96.1%, respectively. Furthermore, the empirical results demonstrate that the classification accuracy rate reaches 92.5% by ANN, 91.1% by DT, and 84.4% by logistic regression two years in advance. The findings of current research provide valuable insights into financial failure prediction and may entice practical implications for stakeholders, especially investors and regulatory bodies, by indicating that the use of the ANN approach may be more effective.

Keywords

• Financial Failure
• Logistic Regression
• Artificial Neural Networks
• Decision Trees

Finansal Başarısızlığın Tahmini: Gelişmiş ve Gelişmekte Olan Ülkelerdeki Halka Açık Şirketlerden Ampirik Kanıtlar

Abstract

Çalışmada yüksek doğruluğa sahip finansal başarısızlık tahmin modelleri oluşturmak üzere gelişmiş ve gelişen ülkelerden 570 şirket 2010 – 2019 dönemi için analiz edilmektedir. Bu çerçevede, lojistik regresyon (LR), yapay sinir ağları (YSA) ve karar ağaçları (KA) uygulanmış ve bahsedilen yöntemlerin sınıflandırma doğrulukları karşılaştırılmıştır. 16 finansal oran bağımsız değişken olarak kullanılmış ve YSA en doğru tahmin sonuçlarını üreterek başarısızlık tahmininde diğer yöntemlere üstünlük sağlamıştır. Diğer bir ifadeyle, YSA başarısızlıktan bir yıl öncesi için %98,1 sınıflama doğruluğu üretirken, LR ve KA sırasıyla %94,7 ve %96,1 doğruluk oranlarına ulaşmışlardır. Buna ek olarak, ampirik sonuçlara göre başarısızlıktan iki yıl öncesi için ANN %92,5, KA %91,1 ve LR %84,4 sınıflama doğruluğu sağlamışlardır. Mevcut çalışmanın bulguları finansal başarısızlık tahminine yönelik ışık tutmaktadır ve YSA yönteminin kullanılmasının daha efektif olabileceğini işaret ederek, özellikle yatırımcılar ve düzenleyici otoriteler gibi paydaşlar açısından pratik sonuçlar ortaya koymaktadır.

Keywords

• Finansal Başarısızlık
• Lojistik Regresyon
• Yapay Sinir Ağları
• Karar Ağaçları

References

1. Aksoy, B. and Boztosun, D. (2021). Comparison of classification performance of machine learning methods in prediction financial failure: Evidence from Borsa Istanbul. Hitit Journal of Social Sciences, 14(1), 56-86. https://doi.org/10.17218/hititsbd.880658
2. Aktan, S. (2011). Application of machine learning algorithms for business failure prediction. Investment Management and Financial Innovations, 8(2), 52-65. Retrieved from https://www.businessperspectives.org/
3. Aktaş, R., Doğanay, M.M. and Yıldız, B. (2003). Mali başarısızlığın öngörülmesi: İstatistiksel yöntemler ve yapay sinir ağı karşılaştırması. Ankara University SBF Journal, 58(4), 1-24. https://doi.org/10.1501/SBFder_0000001691
4. Altaş, D. and Giray, S. (2005). Mali başarısızlığın çok değişkenli istatistiksel yöntemlerle belirlenmesi: Tekstil sektörü örneği. Anadolu University Journal of Social Sciences, 13-28. Retrieved from https://www.ajindex.com/
5. Altınırmak, S. and Karamaşa, Ç. (2016). Comparison of machine learning techniques for analyzing banks’ financial distress. Balıkesir University the Journal of Social Sciences Institute, 19(36), 291-303. https://doi.org/10.31795/baunsobed.645223
6. Altman, E.I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance, 23(4), 589-09. https://doi.org/10.2307/2978933
7. Altunöz, U. (2013). Bankaların finansal başarısızlıklarının yapay sinir ağları modeli çerçevesinde tahmin edilebilirliği. Dokuz Eylül University Faculty of Economics and Administrative Sciences Journal, 28(2), 189 – 217. Retrieved from https://dergipark.org.tr/tr/pub/ije
8. Atiya, A.F. (2001). Bankruptcy prediction for credit risk using neural networks: A survey and new results. IEEE Transactions on Neural Networks, 12(4), 929-935. https://doi.org/10.1109/72.935101

9. Bae, J.K. (2012). Predicting financial distress of the South Korean manufacturing industries. Expert Systems with Applications, 39(10), 9159-9165. https://doi.org/10.1016/j.eswa.2012.02.058
10. Beaver, W.H. (1966). Financial ratios as predictors of failure. Journal of Accounting Research, 71-111. https://doi.org/10.2307/2490171
11. Benli, Y.K. (2005). Bankalarda mali başarısızlığın öngörülmesi lojistik regresyon ve yapay sinir ağı karşılaştırması. Gazi University Journal of Industrial Arts Education Faculty, 16, 31-46. Retrieved from https://dergipark.org.tr/tr/pub/esef
12. Blum, M. (1974). Failing company discriminant analysis. Journal of Accounting Research, 12(1), 1-25. https://doi.org/10.2307/2490525
13. Büyükarıkan, B. and Büyükarıkan, U. (2018). Kimya sektörü işletmelerinde finansal başarısızlığın tahmini. Hacettepe University Journal of Faculty of Economics and Administrative Sciences, 36(3), 29-50. https://doi.org/10.17065/huniibf.290670
14. Canbaz, M. (1998). Erken uyarı göstergeleri olarak finansal oranlar ve çok değişkenli model önerisi (Unpublished doctoral dissertation). Cumhuriyet University, Institute of Social Sciences, Türkiye.
15. Cengiz, D.T., Turanlı, M., Kalkan, S.B. and Köse, I. (2015). Türkiye’deki işletmelerin finansal başarısızlığının faktör analizi ve diskriminant analizi ile incelenmesi. Istanbul University Econometrics and Statistics e-Journal, 23, 62-78. Retrieved from https://dergipark.org.tr/en/pub/ekoist
16. Chung, K.C., Tan, S.S. and Holdsworth, D.K. (2008). Insolvency prediction model using multivariate discriminant analysis and artificial neural network for the finance industry in New Zealand. International Journal of Business and Management, 39(1), 19-28. Retrieved from https://ssrn.com/abstract=1080430
17. Çelik, M.K. (2010). Bankaların finansal başarısızlıklarının geleneksel ve yeni yöntemlerle öngörüsü. Manisa Celal Bayar University the Faculty of Economic and Administrative Sciences Journal of Management and Economics, 17(2), 129-143. Retrieved from https://dergipark.org.tr/en/pub/yonveek
18. Çöllü, D.A., Akgün, L. and Eyduran, E. (2020). Karar ağacı algoritmalarıyla finansal başarısızlık tahmini: Dokuma, giyim eşyası ve deri sektörü uygulaması. International Journal of Economics and Innovation, 6(2), 225-246. https://doi.org/10.20979/ueyd.698738
19. Deakin, E.B. (1972). A discriminant analysis of predictors of business failure. Journal of Accounting Research, 167-179. https://doi.org/10.2307/2490225
20. Doğanay, M.M., Ceylan, N.B. and Aktaş, R. (2006). Predicting financial failure of the Turkish banks. Annals of Financial Economics, 2(1), 97-117. https://doi.org/10.1142/S2010495206500059
21. Edmister, R.O. (1972). An empirical test of financial ratio analysis for small business failure prediction. Journal of Financial and Quantitative Analysis, 7(2), 1477-1493. https://doi.org/10.2307/2329929
22. Gepp, A. and Kumar, K. (2008). The role of survival analysis in financial distress prediction. International Research Journal of Finance and Economics, 16, 12-34. Retrieved from https://research.bond.edu.au/
23. Gogas, P., Papadimitriou, T. and Agrapetidou, A. (2018). Forecasting bank failures and stress testing: A machine learning approach. International Journal of Forecasting, 34(3), 440-455. https://doi.org/10.1016/j.ijforecast.2018.01.009
24. Gregova, E., Valaskova, K., Adamko, P., Tumpach, M. and Jaros, J. (2020). Predicting financial distress of Slovak enterprises: Comparison of selected traditional and learning algorithms methods. Sustainability, 12(10), 3954. https://doi.org/10.3390/su12103954
25. Halim, Z., Shuhidan, S.M. and Sanusi, Z.M. (2021). Corporation financial distress prediction with deep learning: analysis of public listed companies in Malaysia. Business Process Management Journal, 27(4), 1163-1178. https://doi.org/10.1108/BPMJ-06-2020-0273
26. Huang, Y.P. and Yen, M.F. (2019). A new perspective of performance comparison among machine learning algorithms for financial distress prediction. Applied Soft Computing, 83, 105663. https://doi.org/10.1016/j.asoc.2019.105663
27. Hui, X.F. and Sun, J. (2006). An application of support vector machine to companies’ financial distress prediction. In V. Torra, Y. Narukawa, A. Valls and J. Domingo-Ferrer (Eds.), Modeling decisions for artificial intelligence (pp. 274-282). Paper presented at the International Conference on Modeling Decisions for Artificial Intelligence, Tarragona, Spain. https://doi.org/10.1007/11681960_27
28. İçerli, M.Y. and Akkaya, G.C. (2006). Finansal açıdan başarılı olan işletmelerle başarısız olan işletmeler arasında finansal oranlar yardımıyla farklılıkların tespiti. Atatürk University Journal of Economics and Administrative Sciences, 20(1), 413-421. Retrieved from https://dergipark.org.tr/tr/pub/trendbusecon
29. İşseveroğlu, G. and Gücenmez, Ü. (2007). Prediction the financial success in Turkish insurance companies. Ankara University SBF Journal, 62(4), 125-140. https://doi.org/10.1501/SBFder_0000002096
30. Jan, C.I. (2021). Financial information asymmetry: Using deep learning algorithms to predict financial distress. Symmetry, 13(3), 443. https://doi.org/10.3390/sym13030443
31. Jo, H., Han, I. and Lee, H. (1997). Bankruptcy prediction using case-based reasoning, neural networks, and discriminant analysis. Expert Systems with Applications, 13(2), 97-108. https://doi.org/10.1016/S0957-4174(97)00011-0
32. Karacan, S. and Savcı, M. (2011). Kriz dönemlerinde işletmelerin mali başarısızlık nedenleri. Kocaeli University Journal of Social Sciences, 21(1), 39-54. Retrieved from https://dergipark.org.tr/tr/pub/kosbed
33. Kulalı, I. (2016). Altman Z-Skor modelinin BİST şirketlerinin finansal başarısızlık riskinin tahmin edilmesinde uygulanması. International Journal of Management Economics and Business, 12(27), 283-292. https://doi.org/10.17130/10.17130/ijmeb.2016.12.27.1076
34. Le, H.H. and Viviani, J.L. (2018). Predicting bank failure: An improvement by implementing a machine-learning approach to classical financial ratios. Research in International Business and Finance, 44, 16-25. https://doi.org/10.1016/j.ribaf.2017.07.104
35. Lin, T.H. (2009). A cross model study of corporate financial distress prediction in Taiwan: Multiple discriminant analysis, logit, probit and neural networks models. Neurocomputing, 72(16), 3507-3516. https://doi.org/10.1016/j.neucom.2009.02.018
36. Malakauskas, A. and Lakstutiene, A. (2021). Financial distress prediction for small and medium enterprises using machine learning techniques. Engineering Economics, 32(1), 4-14. https://doi.org/10.5755/j01.ee.32.1.27382
37. Meyer, P.A. and Pifer, H.W. (1970). Prediction of bank failures. The Journal of Finance, 25(4), 853-868. https://doi.org/10.1111/j.1540-6261.1970.tb00558.x
38. Mselmi, N., Lahiani, A. and Hamza, T. (2017). Financial distress prediction: The case of French small and medium-sized firms. International Review of Financial Analysis, 50, 67-80. https://doi.org/10.1016/j.irfa.2017.02.004
39. Noviantoro, T. and Huang, J.P. (2021). Comparing machine learning algorithms to investigate company financial distress. Review of Business, Accounting & Finance, 1(5), 454-479. Retrieved from https://asosindex.com.tr/
40. Odom, M.D. and Sharda, R. (1990). A neural network model for bankruptcy prediction. In INNS (Ed.), 1990 IJCNN international joint conference on neural networks (pp. 163-168). Papers presented at the International Joint Conference on Neural Networks (IJCNN), San Diego, California, USA. https://doi.org/10.1109/IJCNN.1990.137710
41. Ohlson, J.A. (1980). Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research, 18(1), 109-131. https://doi.org/10.2307/2490395
42. Oribel, T. and Hanggraeni, D. (2021). An application of machine learning in financial distress prediction cases in Indonesia. International Journal of Business and Technology Management, 3(2), 98-110. Retrieved from https://myjms.mohe.gov.my/index.php/ijbtm/index
43. Özdemir, F.S. (2011). Finansal raporlama sistemlerinin bilginin ihtiyaca uygunluğu açısından değerlendirilmesi: İMKB şirketlerinde finansal başarısızlık tahminleri yönüyle bir uygulama (Unpublished doctoral dissertation). Ankara University, Institute of Social Sciences, Turkey.
44. Petropoulos, A., Siakoulis, V., Stavroulakis, E. and Vlachogiannakis, N.E. (2020). Predicting bank insolvencies using machine learning techniques. International Journal of Forecasting, 36(3), 1092-1113. https://doi.org/10.1016/j.ijforecast.2019.11.005
45. Qian, H., Wang, B., Yuan, M., Gao, S. and Song, Y. (2022). Financial distress prediction using a corrected feature selection measure and gradient boosted decision tree. Expert Systems with Applications, 190, 116202. https://doi.org/10.1016/j.eswa.2021.116202
46. Ravi, V. and Pramodh, C. (2008). Threshold accepting trained principal component neural network and feature subset selection: Application to bankruptcy prediction in banks. Applied Soft Computing, 8(4), 1539-1548. https://doi.org/10.1016/j.asoc.2007.12.003
47. Selimoğlu, S. and Orhan, A. (2015). Finansal başarısızlığın oran analizi ve diskriminant analizi kullanılarak ölçümlenmesi: BİST’de işlem gören dokuma, giyim eşyası ve deri işletmeleri üzerine bir araştırma. The Journal of Accounting and Finance, 66, 21-40. https://doi.org/10.25095/mufad.396529
48. Tang, X., Li., S., Tan, M. and Shi, W. (2020). Incorporating textual and management factors into financial distress prediction: A comparative study of machine learning methods. Journal of Forecasting, 39(5), 769-787. https://doi.org/10.1002/for.2661
49. Terzi, S. (2011). Finansal rasyolar yardımıyla finansal başarısızlık tahmini: Gıda sektöründe ampirik bir araştırma. Journal of Çukurova University Faculty of Economics and Administrative Sciences, 15(1), 1-18. Retrieved from https://dergipark.org.tr/tr/pub/cuiibfd
50. Torun, T. (2007). Finansal başarısızlık tahmininde geleneksel istatistiki yöntemlerle yapay sinir ağlarının karşılaştırılması ve sanayi işletmeleri üzerinde uygulama (Unpublished doctoral dissertation). Erciyes University, Insitute of Social Sciences, Türkiye.
51. Ural, K., Gürarda, Ş. and Önemli, M.B. (2015). Lojistik regresyon modeli ile finansal başarısızlık tahminlemesi: Borsa İstanbul’da faaliyet gösteren gıda, içki ve tütün şirketlerinde uygulama. The Journal of Accounting and Finance, 67, 85-100. https://doi.org/10.25095/mufad.396578
52. Ünsal, A. (2001). Mali başarılı ve mali başarısız şirketlerin ayırımını sağlayan diskriminant fonksiyonunun bulunması. Çukurova University Social Sciences Institute Journal, 7(7), 214-234. Retrieved from https://dergipark.org.tr/tr/pub/cusosbil
53. Vieira, A.S., Duarte, J., Riberio, B. and Neves, J.C. (2009). Accurate prediction of financial distress of companies with machine learning algorithms. In M. Kolehmainen, P. Toivanen and B. Beliczynski (Eds.), Proceedings 9th international conference on adaptive and natural computing algorithms (pp. 569-576). Papers presented at the 9th International Conference on Adaptive and Natural Computing Algorithms, Kuopio, Finland. https://doi.org/10.1007/978-3-642-04921-7_58
54. Vuran, B. (2009). Prediction of business failure: A comparison of discriminant and logistic regression analyses. Istanbul University Journal of the School of Business, 38(1), 47-65. Retrieved from https://iupress.istanbul.edu.tr/en/journal/ibr/home
55. Wu, D.D., Liang, L. and Yang, Z. (2008). Analyzing the financial distress of Chinese public companies using probabilistic neural networks and multivariate discriminate analysis. Socio-Economic Planning Sciences, 42(3), 206-220. https://doi.org/10.1016/j.seps.2006.11.002
56. Yakut, E. and Elmas, B. (2013). İşletmelerin finansal başarısızlığının veri madenciliği ve diskriminant analizi modelleri ile tahmin edilmesi. Afyon Kocatepe University Journal of Economics and Administrative Sciences, 15(1), 237-254. Retrieved from https://dergipark.org.tr/en/pub/akuiibfd
57. Yap, B.C.F., Yong, D.G.F. and Poon, W.C. (2010). How well do financial ratios and multiple discriminant analysis predict company failures in Malaysia. International Research Journal of Finance and Economics, 54, 166-175. Retrieved from https://research.monash.edu/
58. Yıldız, B. (2001). Prediction of Financial Failure with Artificial Neural Network Technology and an Empirical Application on Publicly Held Companies. The ISE Review, 5(17), 51-67. Retrieved from https://www.borsaistanbul.com/
59. Yousaf, U.B., Jebran, K. and Wang, M. (2022). A comparison of static, dynamic and machine learning models in predicting the financial distress of Chinese firms. Romanian Journal of Economic Forecasting, 25(1), 122-138. Retrieved from https://ipe.ro/new/rjef.htm
60. Zmijewski, M.E. (1984). Methodological issues related to the estimation of financial distress prediction models. Journal of Accounting Research, 22, 59-82. https://doi.org/10.2307/2490859