Comparison of Machine Learning Methods in Prediction of Financial Failure of Businesses in The Manufacturing Industry: Evidence from Borsa İstanbul

Öz In this study, Artificial Neural Networks (NN), C5.0 Classification Algorithm, Classification and Regression Trees (CART) analyses were used to predict the financial success/failure of 126 businesses that are operating in the BIST (Borsa İstanbul) Manufacturing Industry Sector. The data contains the years 2006 to 2009. In the study, 25 quantitative variable and 4 qualitative variable were used. The overall classification accuracy from the highest to the lowest of 3 years prior to successful-failure year (for 2006) is 84.21% for CART, 81.58% for ANN and 76.32% for C5.0, respectively. The overall classification accuracy from the highest to the lowest of 2 years prior to successful-failure year (for 2007) is 86.84% for CART, 84.21% for ANN, 78.95% for C5.0, respectively. The overall classification accuracy from the highest to the lowest of 1 year prior to successful-failure year (for 2008) is 92.11% for CART, 92.11 for ANN and 86.84% for C5.0, respectively. ANN and CART models are notable in terms of their ability to predict upcoming financial failure of unsuccessful businesses with 100% classification accuracy from a year ago. The prediction of the financial success/failure by the three models obtained in the study more than one, two and three years ago shows that the models used in this study can be included in the model used by those concerned.

Anahtar Kelimeler:

Financial Failure Prediction, Borsa İstanbul, Artificial Neural Networks, C5.0 Decision Rule Algorithm, CART Classification and Regression Trees

PDF

___

Akgüç, Ö. (1997). Financial Management, İstanbul: Avcıol publications.

Aksoy, B. & Ertaş, F. C. (2016). Effects of corporate merger and acquisition on target company financial performance. Academic View Review, 54, 772-786.

Aktaş, Ramazan, M. Mete Doğanay & Birol Yıldız (2003). Forecasting financial failure: comparison of statistical methods and artificial neural network. Ankara University SBF Journal, 58(4), 1-24. Access address: https://app.trdizin.gov.tr/publication/paper/detail/TWpZME1URT0

Altman, E. I., T. Kant & T. Rattanaruengyot (2009). Bankruptcy performance: Avoiding”, Journal of Applied Corporate Finance, 21(3), 50-65. Access address: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=1495296

Baixauli, J. S. & Mo´dica-Milo, A. (2010). The bias of unhealthy smes ın bankruptcy prediction models. Journal of Small Business and Enterprise Development, 17(1), 60-77. Access address: https://www.emerald.com/insight/content/doi/10.1108/14626001011019134/full/pdf

Beaver, William H. (1968). Market prices, financial ratios, and the prediction of failure. Journal of Accounting Research, 6(2), 179-192. Access address: https://www.jstor.org/stable/2490233?seq=1#metadata_info_tab_contents

Bee, Thai Siew & Mehdi Abdollahi (2013). Corporate failure prediction: Malaysia’s emerging market. The International Journal of Finance, 25(4), 7985-8008. Access address: https://www.econbiz.de/Record/corporate-failure-prediction-malaysia-s-emerging-market-bee-thai-siew/10010382959

Bilir, H.. (2015). Definition and market oriented solution of financial distress: Debt structuring, asset sales and new capital injection. Socioeconomic,1, 9-24. Access address: http://eds.a.ebscohost.com/eds/pdfviewer/pdfviewer?vid=0&sid=8f6841cb-c699-4e01-959d-f18901710107%40sessionmgr4007

Brealey, R. & Myers, S. C., Trans. Bozkurt, A. J., Arıkan T., & Doğukanlı, H. (2007), Fundamentals of Business Finance, İstanbul: MC Graw Hill and Literature publications.

Chandra, D. K., Ravi, V. & Bose, I. (2009). Failure prediction of DOTCOM companies using hybrid intelligent techniques. Expert Systems with Applications, 36, 4830-4837. Access address: https://www.sciencedirect.com/science/article/pii/S0957417408002741

Chen, J., Marshall, B. R., Zhang, J., & Ganesh, S. (2006). Financial distress prediction in China. Review of Pacific Basin Financial Markets and Policies, 9(2), 317-336. Access address: https://econpapers.repec.org/article/wsirpbfmp/v_3a09_3ay_3a2006_3ai_3a02_3an_3as0219091506000744.htm

Chen, Mu-Y.. (2011). Bankruptcy prediction in firms with statistical and intelligent techniques and a comparison of evolutionary computation approaches. Computers and Mathematics with Applications, 62, 4514-4524. Access address: https://www.sciencedirect.com/science/article/pii/S0898122111008947

Chen, Mu-Y.. (2011). Predicting corporate financial distress based on integration of decision tree classification and logistic regression. Expert Systems with Applications, 38, 11261-11272. Access address: https://www.sciencedirect.com/science/article/pii/S0957417411003976

Chen, Mu-Y.. (2014). Using a hybrid evolution approach to forecast financial failures for Taiwan-listed companies. Quantitative Finance, 14(6), 1047-1058. Access address: https://www.tandfonline.com/doi/full/10.1080/14697688.2011.618458

Chuang, Chun-L.. (2013). Application of hybrid case-based reasoning for enhanced performance in bankruptcy prediction. Information Sciences, 236, 174-185. Access address: https://www.researchgate.net/publication/256721212_Application_of_hybrid_case-based_reasoning_for_enhanced_performance_in_bankruptcy_prediction

Çalış, A., Kayapınar, S. & Çetinyokuş, T. (2011). An application on computer and internet security with decision tree algorithms in data mining. Journal of Industrial Engineering, 25(3-4), 2-19. Access address: https://dergipark.org.tr/en/download/article-file/752270

Çelik, M. K. (2010). Prediction of Financial Failure of Banks with Traditional and New Methods. Management and Economy, 17(2), 129-143. Access address: https://dergipark.org.tr/tr/pub/yonveek/issue/13693/165725

Çelik, U., Akçetin, E., & Gök, M.. (2017), Data mining with rapidminer, İstanbul: Pusula publications.

Delen, D., Kuzey, C. & Uyar, A.. (2013). Measuring firm performance using financial ratios: A decision tree approach. Expert Systems with Applications, 40, 3970-3983. Access address: https://www.sciencedirect.com/science/article/pii/S0957417413000158

Dener, M. & Orman, A. (2009). Open source data mining programs: sample practice in WEKA”, Conference: Conference: XI. Academic Informatics Conference, Şanlıurfa, January 2009, 1-11. Access address: https://ab.org.tr/ab09/kitap/dener_dorterler_AB09.pdf

Doğrul, Ü. (2009), Financial failure and prediciton of financial failure: An application on industry companies trading in İstanbul Stock Exchange, Mersin University, Institute of Social Sciences, Mersin, (Unpublished Master’s Thesis).

Gaganis, C. (2009). Classification techniques for the identification of falsified financial statements: a comparative analysis. Intelligent Systems in Accounting, Finance and Management, 16, 207-229. Access address: https://www.researchgate.net/publication/ 220613891

Gallego-Garcia, A., Mures-Quintana, M.-J.. (2012). Business failure prediction models: finding the connection between their results and the sampling method. Preparation of Electronic Manuscripts for Publication, 157-168. Access address: https://www.researchgate.net/publication/286361899

Geng, R., Bose, I. & Chen, X. (2015). Prediction of financial distress: an empirical study of listed chinese companies using data mining. European Journal of Operational Research, 241, 236-247. Access address: https://www.sciencedirect.com/science/article/pii/S0377221714006511

Gepp, A., Kumar, K. & Bhattacharya, S. (2010). Business failure prediction using decision tree. Journal of Forecasting, 29, 536-555. Access address: https://ideas.repec.org/a/jof/jforec/v29y2010i6p536-555.html

Gepp, A. & Kuldeep K. (2015). Predicting financial distress: a comparison of survival analysis and decision tree techniques. Procedia Computer Science, 54, 396-404. Access address: https://www.sciencedirect.com/science/article/pii/S1877050915013708

Glezakos, M., Mylonakis J. & Oikonomou K. (2010). An empirical research on early bankruptcy forecasting models: Does logit analysis enhance business failure predictability? European Journal of Finance and Banking Research, 3(3), 1-15. Access address: http://globip.com/contents/articles/european-vol3-article1.pdf

Iwan, M. (2005). Bankruptcy prediction model with zeta optimal cut-off score to correct type ı errors. Gadjah Mada International Journal of Business, 7(1), 41-68. Access address: https://www.researchgate.net/publication/277071919_Bankruptcy_prediction_model_with_zetac_optimal_cut-off_score_to_correct_type_I_errors

Jackson, Richard H.G. & Wood, A. (2013). The performance of insolvency prediction and credit risk models in the UK: a comparative study. The British Accounting Review, 45, 183-202. Access address: https://www.researchgate.net/publication/259133786

Jardin, P. D. (2009). Bankruptcy prediction models: how to choose the most relevant variables. Bankers, Markets and Investors, 98, 39-46. Access address: https://www.researchgate.net/publication/235643766

Jardin, P. D. (2012). The influence of variable selection methods on the accuracy of bankruptcy prediction models. Bankers, Markets and Investors, 116, 20-39. Access address: https://www.researchgate.net/publication/235643793

Kılıç, Y. (2011), Financial faıilure prediction using data mining: an application in İstanbul Stock Exchange, Gaziantep University, Institute of Social Sciences, Gaziantep, (Unpublished Master’s Thesis). Access address: https://tezarsivi.com/finansal-basarisizlik-tahmininde-veri-madenciliginin-kullanilmasi-imkbde-bir-uygulama

Kılıç, Y. & Seyrek, İ. H. (2016). Use of artificial neural networks in forecasting financial failure: an application in manufacturing sector. www.researchgate.net. Berlin, 2016, s. 1-15. Access address: https://www.researchgate.net/publication/296705043

Koç, S. & Ulucan, S.. (2016). Testing of Altman z methods which is used for detecting of financial failures with fuzzy logic (anfis) technique: a case study on technology and textile sector. Revenue and Finance Articles, 106, 147-167. Access address: https://dergipark.org.tr/en/download/article-file/259955

Le, H. H. & 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. Access address: https://ideas.repec.org/a/eee/riibaf/v44y2018icp16-25.html

Li, H. & Sun, J. (2013). Predicting business failure using an rsf-based case-based reasoning ensemble forecasting method. Journal of Forecasting, 32, 180-192. Access address: https://www.researchgate.net/publication/263113267

Liang, D., Tsai, C.-F. & Wu, H.-T. (2015). The effect of feature selection on financial distress prediction. Knowledge-Based Systems, 73, 289-297. Access address: https://isslab.csie.ncu.edu.tw/download/publications/5.pdf

Lussier, R. N. (1995). A nonfinancial business success versus failure prediction model for young firms. Journal of Small Business Management, 1995, 8-20. Access address: https://www.questia.com/library/journal/1G1-16787401/a-nonfinancial-business-success-versus-failure-prediction

Misund, B. (2017). Financial ratios and prediction on corporate bankruptcy in the Atlantic salmon industry. Aquaculture Economics & Management, 21(2), 241-260. Access address: https://www.researchgate.net/publication/304611502

Muller, G.H., Steyn-Bruwer, B.W. & Hamman, W.D. (2009). Predicting financial distress of companies listed on the JSE- a comparison of techniques. S.Afr.J.Bus.Manage, 40(1), 21-32. Access address: https://www.researchgate.net/publication/286881166

Okay, K. (2015). Predicting business failures in non-financial turkish companies, İhsan Doğramacı Bilkent University Graduate School of Economics and Social Sciences, Ankara (Unpublished Masters Thesis). Access address: http://www.thesis.bilkent.edu.tr/0006970.pdf

Öcal, N., Ercan, M. K. & Kadıoğlu, E. (2015). Predicting financial failure using decision tree algorithms: an empirical test on the manufacturing industry at Borsa İstanbul. International Journal of Economics and Finance, 7(7), 189-206. Access address: https://www.researchgate.net/publication/281269848

Özdağoğlu, G., Özdağoğlu, A., Gümüş, Y. & Kurt-Gümüş, G. (2017). The application of data mining techniques in manipulated financial statement classification: the case of Turkey. Journal of AI and Data Mining, 5(1), 67-77. Access address: http://jad.shahroodut.ac.ir/article_664.html

Özkan, M. & Boran, L. (2014). Usage of data mining at financial decision making. Çankırı Karatekin University Faculty of Economics and Administrative Sciences Journal, 4(1), 59-82. Access address: https://dergipark.org.tr/en/download/article-file/382288

Öztemel, E. (2012). Artificial Neural Networks, İstanbul: Papatya publications.

Sayılgan, G. & Ece, A. (2016). Bankruptcy postponement and panoramic analysis on bankruptcy postponement litigations in Turkey between 2009-2013. Revenue and Finance Articles, 105, 47-74. Access address: https://dergipark.org.tr/tr/download/article-file/259954

Selimoğlu, S. & Orhan, A. (2015). Measurement of financial failure by using ratio analysis and discriminant analysis: a research on woven, clothing and leather enterprises in BIST. Journal of Accounting and Finance, April, 21-40. Access address: https://www.researchgate.net/publication/323406251

Sun, J., Li, H., Huang, Q. H. & He, K-Yu. (2014). Predicting financial distress and corporate failure: a review from the state-of-the-art definitions, modeling, sampling, and featuring approaches. Knowledge-Based Systems, 57, 41-56. Access address: https://www.sciencedirect.com/science/article/pii/S0950705113003869

Tuncay, M. (2011). Corporate financial restructuring after financial crises. Journal of Accounting and Finance, 103-118. Access address: https://dergipark.org.tr/tr/download/article-file/426903

Tsai, C. F., Hsu, Y. F. & Yen D. C. (2014). A comparative study of classifier ensembles for bankruptcy prediction. Applied Soft Computing, 24, 977-984. Access address: https://www.sciencedirect.com/science/article/pii/S1568494614004128

Uzar, C. (2013). The usage of data mining technology in financial ınformation system: an application on Borsa Istanbul, Dokuz Eylül University Social Sciences Institute, İzmir (Unpublished PhD Thesis).

Wu, W., Lee, V. C. S., & Tan T. Y. (2006). Data preprocessing and data parsimony in corporate failure forecast models: evidence from Australian materials industry. Accounting and Finance, 46, 327-345. Access address: https://www.researchgate.net/publication/4737947

Yakut, E. & Elmas, B. (2013). Estimating financial failure of enterprises with data mining and discriminant analysis. Afyon Kocatepe University İİBF Journal, 15(1), 237-254. Access address: https://dergipark.org.tr/tr/pub/eab/issue/39985/475267

Yakut, E. (2012). The Comparison of the classification successes of the artifical neural networks through data mining techniques of c5.0 algorithm and supporting vector machines: an application in manufacturing sector, Atatürk University Social Sciences Institute, Erzurum (Unpublished PhD Thesis). Access address: https://tezarsivi.com/veri-madenciligi-tekniklerinden-c50-algoritmasi-ve-destek-vektor-makineleri-ile-yapay-sinir-aglarinin-siniflandirma-basarilarinin-karsilastirilmasi-imalat-sektorunde-bir-uygulama

Yapraklı, T. Ş. & Erdal, H.. (2016). Firm failure prediction: a case study based on machine learning. Journal of Information Technologies, 9(1), 21-31. Access address: https://dergipark.org.tr/tr/pub/gazibtd/issue/26691/280780

Yip, A. Y. N. (2006). Business failure prediction: a case-based reasoning approach. Review of Pacific Basin Financial Markets and Policies, 9(3), 491-508. Access address: https://www.Business failure prediction: a case-based reasoning approach. Review of Pacific Basin Financial Markets and Policiesworldscientific.com/doi/abs/10.1142/S021909150600080X