Firma Başarısızlığı Tahminlemesi: Makine Öğrenmesine Dayalı Bir Uygulama

Öz Firma risk profilinin belirlenmesi, literatürde firma başarısızlığı kavramlarıyla incelenmektedir. Bu konu üzerinde, özellikle 1929 büyük buhranı sonrasında çok önemli çalışmalar yapılmıştır. Başlarda, riskli ve başarılı firmaların finansal göstergeleri arasındaki farklılıklara yoğunlaşılırken, özellikle bilişim teknolojilerindeki gelişimlere paralel olarak son yıllarda bilişim sistemleri firma başarısızlığı tahminlemesinde en önemli bileşenlerinden biri olmuştur. Özellikle, makine öğrenmesi yöntemlerinin bu alanda kullanılmaya başlanmasıyla firma başarısızlığının tahmin edilmesinde önemli yol kat edilmiştir. Bu çalışmada Erzurum ilinde 38 yıldır faaliyet gösteren inşaat malzemeleri toptancısı bir firmanın müşterilerinin vadeli borçlarını ödeme/ödememe riskleri firma başarısızlığı kapsamında ele alınmış ve firma başarısızlığının tahmininde uygun bir makine öğrenmesi yöntemi araştırılmıştır. Probleme etki eden değişkenler Temel Bileşenler Analizi (TBA) ile ortaya konulmuştur. Son yıllarda makine öğrenmesinde oldukça gelişmekte olan Yapay Sinir Ağları (YSA) ve Destek Vektör Makineleri (DVM)’nin TBA yöntemiyle beraber kullanımıyla oluşturulan hibrit modellerin bu tahminde uygulanabilirliği incelenmiş ve tahmin performansları yalın YSA ve DVM’ler ile karşılaştırılmıştır. TBA ile bütünleşik olarak kullanılan hibrit modellerin tahmin başarısının yalın YSA ve DVM’lere oranla daha tatmin edici sonuçlar verdiği görülmüştür. Özellikle TBA-DVM modelinin firma başarısızlığı tahminlemesinde alternatif bir yöntem olarak etkin bir şekilde kullanılabileceği sonucuna varılmıştır.

Anahtar Kelimeler:

Firma Başarısızlığı, Makine Öğrenmes; Sınıflandırma; Temel Bileşenler Analizi; Yapay Sinir Ağları; Destek Vektör Makineleri

PDF

___

[1] E.I. Altman, "Corporate Distress Prediction Models in Turbulent Economic and Basel II Environment", http://pages.stern.nyu.edu/~ealtman/Corp-Distress.pdf, 2002.
[2]J. Wilcox, "A prediction of business failure using accounting data", Empirical Research in Accounting, 2, 163-179, 1973.
[3] T. Sung, N. Chang, ve G. Lee, "Dynamics of modeling in data mining: Interpretive approach to bankruptcy prediction", Journal of Management Information Systems, 16(1), 63-85, 1999.
[4] E.I. Altman, "Financial ratios, discriminant analysis and the prediction of corporate bankruptcy", Journal of Finance, 23(3), 589- 609, 1968.
[5] E.I. Altman, R. Haldeman ve P. Narayanan, "ZETA analysis: A new model to identify bankruptcy risk of corporations", Journal of Banking and Finance, 1(1), 29-54, 1977.
[6] P.A. Meyer ve H.W. Pifer,"Prediction of bank failures", The Journal of Finance, 25( 4), 853-68, 1970.
[7] D. Martin, "Early warning of bank failure: A logit regression approach", Journal of banking and finance, 1(3), 249-276, 1977.
[8] J. Ohlson, "Financial ratios and the probabilistic prediction of bankruptcy", Journal of Accounting Research, 18(1), 109-131, 1980.
[9] M.E. Zmijewski, "Methodological issues related to the estimation of financial distress prediction models", Journal of Accounting Research, 59-82, 1984.
[10] R.C. West, "A factor analytic approach to bank condition",Journal of Banking and Finance, 9, 253-266, 1985.
[11] H. Frydman, E.I. Altman ve D. Kao, "Introducing recursive partitioning for financial classification: The case of financial distress",Journal of Finance, 40(1), 269-291, 1985.
[12] W.F. Messier. ve J. Hansen, "Inducing rules for expert system development: An example using default and bankruptcy data", Management Science, 34(12), 1403-1415, 1988.
[13] A.I. Dimitras, S.H. Zanakis ve C. Zopounidis, "A survey of business failures with an emphasis on prediction methods and industrial applications", European Journal of Operational Research, 90(3), 487-513, 1996.
[14]A.W. Lo, "Logit versus discriminant analysis: a specification test and application to corporate bankruptcies", Journal of Econometrics, 31(2), 151-178, 1986.
15. W. Wu, V.C.S. Lee ve T.Y. Tan, "Data preprocessing and data parsimony in corporate failure forecast models: evidence from Australian materials industry", Accounting and Finance, 46(2), 327- 345, 2006.
[16]M.M. Hamer, "Failure prediction: sensitivity of classification accuracy to alternative statistical methods and variable sets", Journal of Accounting and Public Policy, 2, 289-307, 1983.
[17] A. Charitou, E. Neophytou ve C. Charalambous,"Predicting corporate failure: empirical evidence for the UK", European Accounting Review, 13(3), 465-497, 2004.
[18]P. Ravi Kumar ve V. Ravi "Bankruptcy prediction in banks and firms via statistical and intelligent techniques-A review", European Journal of Operational Research, 180(1), 1-28, 2007.
[19]K.S. Shin, T.S. Lee ve H.J. Kim, "An application of support vector machines in bankruptcy prediction model", Expert Systems with Applications, 28(1), 127-135, 2005.
[20]G.P. Zhang, M.Y. Hu, E.B. Patuwo ve D.C. Indro, "Artificial neural networks in bankruptcy prediction: General framework and crossvalidation analysis",European Journal of Operational Research, 116(1), 16-32, 1999.
[21]F. Ciampi ve N. Gordini,"Small enterprise default prediction modeling through artificial neural networks: An empirical analysis of Italian small enterprises",Journal of Small Business Management, 51(1), 23-45, 2013a.
[22]S.H. Min ve J. Lee, "Bankruptcy prediction using support vector machine (SVM) with optimal choice of kernel function parameters",Expert System with Applications, 28, 603-614, 2005.
[23]S.H. Min, J. Leeve I. Han, "Hybrid genetic algorithms and support vector machines for bankruptcy prediction", Expert System with Applications, 31, 652-660, 2006.
[24]H.S. Kim ve S.Y. Sohn, "Support vector machines for default prediction of SMEs based on technology credit",European Journal of Operational Research, 201, 838-846, 2010.
[25]B. Back, T. Laitinen ve K. Sere, "Neural network and genetic algorithm for bankruptcy prediction", Expert Systems with Applications, 11(4), 407-413, 1996.
[26]R. Barniv, A. Anurag ve R. Leach, "Predicting the out come following bankruptcy filing: A three state classification using NN", International Journal of Intelligent Systems in Accounting Finance and Management, 6, 177-194, 1997.
[27]B.A. Ahn, S.S. Cho ve C.Y. Kim, "The integrated methodology of rough set theory and artificial neural network for business failure prediction", Expert Systems with Applications, 18, 65-74, 2000.
[28]H. Bian ve L. Mazlack, "Fuzzy-rough nearest neighbour classification approach", in: 22nd International Conference of the North American Fuzzy Information Processing Society, (NAFIPS 2003) Proceedings Chicago, 500-505, 2003.
[29]A. Cielen, L. Peeters ve K. Vanhoof, "Bankruptcy prediction using a data envelopment analysis",European Journal of Operational Research, 154, 526-532, 2004.
[30]A.Y.N. Yip, "Predicting business failure with a case-based reasoning approach, lecture notes in computer science, in: M.G. Negoita, R.J. Howlett, L.C. Jain (Eds.), Knowledge-Based Intelligent Information and Engineering Systems", 8th International Conference, (KES 2004), Wellington, New Zealand, 20-25 Eylül 2004.
[31]J.D. Andres, M. Landajove P. Lorca, "Forecasting business profitability by using classification techniques: A comparative analysis based on a Spanish case", European Journal of Operational Research, 167, 518-542, 2005.
[32]Z. Hua, Y. Wang, X. Xu, B. Zhang ve L. Liang, "Predicting corporate financial distress based on integration of support vector machine and logistic regression", Expert Systems with Applications,33(2), 434-440, 2007.
[33]R.H. Lin, Y.T. Wang, C.H. Wu ve C.L. Chuang, "Developing a business failure prediction model via RST, GRA and CBR",Expert Systems with Applications, 36(2), 1593-1600, 2009.
[34]H. Youn ve Z. Gu, "Predicting Korean lodging firm failures: An artificial neural network model along with a logistic regression model", International Journal of Hospitality Management, 29, 120-127, 2010.
[35]A. Chaudhuri ve K. De, "Fuzzy support vector machine for bankruptcy prediction",Applied Soft Computing, 11(2), 2472-2486, 2011.
[36]H. Li ve J. Sun, "On performance of case-based reasoning in Chinese business failure prediction from sensitivity, specificity, positive and negative values",Applied Soft Computing, 11(1), 460-467, 2011.
[37]N. Benhayoun, I. Chairi, A. El Gonnouni ve A. Lyhyaoui, "Financial intelligence in prediction of firm's creditworthiness risk: Evidence from support vector machine approach",Procedia Economics and Finance, 5, 103-112, 2013.
[38]N. Gordini, "A genetic algorithm approach for SMEs bankruptcy prediction: Empirical evidence from Italy",Expert Systems with Applications, 41, 6433-6445, 2014.
[39]T. Bieliková, T. Bányiová ve A. Piterková, "Prediction techniques of agriculture enterprises failure",Procedia Economics and Finance, 12, 48-56, 2014.
[40]W. Xu, Z. Xiao, X. Dang, D. Yang ve X. Yang, "Financial ratio selection for business failure prediction using soft set theory", Knowledge-Based Systems, 63, 59-67, 2014.
[41]I. Stanimirova, M. Daszykowskive B. Walczak, "Dealing with values and outliers in principal component analysis", Talanta, 72(1), 172-178, 2007.
[42]M. Çilli, İnsan hareketlerinin modellenmesi ve benzeşiminde temel bileşenler analizi yönteminin kullanılması, Doktora Tezi, Hacettepe Üniversitesi, Sağlık Bilimleri Enstitüsü, 2007.
[43]P. Berkhin, Survey of clustering data mining techniques, Accrue SoftwareInc., San Jose, California, USA, 2002.
[44]L. Sangün, L., Temel bileşenler analizi, ayırma analizi, kümeleme analizleri ve ekolojik verilere uygulanması üzerine bir araştırma, Doktora Tezi, Çukurova Üniversitesi, Fen Bilimleri Enstitüsü, 2007.
[45]Hassoun, M.H., Fundamentals of artificial neural networks, MIT press, USA, 1995.
[46]Graupe, D., Principles of artificial neural networks, World Scientific, 6.Baskı, 2007.
[47]H. Erdal, "Makine Öğrenmesi Yöntemlerinin İnşaat Sektörüne Katkısı: Basınç Dayanımı Tahminlemesi". Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 21(3), 109-114, 2015.
[48]Internet: Cornell Üniversitesi Resmi İnternet Sayfası,"Support Vector Machines",www.math.cornell. Edu/~numb3rs/kostyuk/num219.htm, 16.11. 2014.
[49]X. Xu, C. Zhou ve Z. Wang, "Credit scoring algorithm based on link analysis ranking with support vector machine",Expert Systems with Applications, 36(2), 2625-2632, 2009.
[50]S. Lucey, "Enforcing non-positive weights for stable support vector tracking", Computer Vision and Pattern Recognition, CVPR 2008. IEEE Conference on, 1-8, 23-28 Haziran 2008.
[51]W.C. Hong, "Chaotic particle swarm optimization algorithm in a support vector regression electric load forecasting model",Energy Conversion and Management, 50(1), 105-117, 2009.
[52]S. Piramuthu, "Financial credit-risk evaluation with neural neurofuzzy systems", European Journal of Operation Research, 112(2), 310-321, 1999.
[53] A. Vellido, P.J.G. Lisboa ve J. Vaughan, "Neural networks in business: a survey of application (1992-1998)", Expert System With Application, 17, 51-70, 1999.
[54]A.B. Graf ve S. Borer, "Normalization in support vector machines", In Pattern Recognition, Springer Berlin Heidelberg, 277-282, 2001.
[55]H. Yumurtacı Aydoğmuş, A. Ekinci, H.İ. Erdal ve H. Erdal, "Optimizing the monthly crude oil price forecasting accuracy via bagging ensemble models", Journal of Economics and International Finance, 7(5), 127-136, 2015.
[56]A. Chaudhuria ve K. Deb, "Fuzzy Support Vector Machine for bankruptcy prediction", Applied Soft Computing, 11, 2472-2486, 2011.
[57]B. Ribeiro, C. Silva, N. Chen, A. Vieira veJ.C. Das Neves, "Enhanced default risk models with SVM+", Expert Systems with Applications, 39, 10140-10152, 2012.
[58]K.S. Shin, T.S. Lee veH.J. Kim, "An application of support vector machines in bankruptcy prediction model", Expert System With Application, 28, 127-135, 2005.
[59]Y.S. Ding, X.P. Song veY.M. Zen, "Forecasting financial condition of Chinese listed companies based on support vector machine", Expert Systems with Applications, 34, 3081-3089, 2008.
[60]C.F. Tsai, "Feature selection in bankruptcy prediction", Knowledge-Based Systems, 22, 120-127, 2009.
[61]N. Benhayouna, I. Chairia, A. El Gonnounia veA. Lyhyaouia, "Financial Intelligence in Prediction of Firm's Creditworthiness Risk: Evidence from Support Vector Machine Approach", Procedia Economics and Finance, 5, 103-112, 2013.
[62]D. Delen, C. Kuzey veA. Uyar, "Measuring firm performance using financial ratios: A decision tree approach", Expert Systems with Applications, 40, 3970-3983, 2013.