Predicting Bankruptcy at Polish Companies: A Comparison of Selected Machine Learning and Deep Learning Algorithms

Joanna Wyrobek

Streszczenie


Tytuł artykułu: Prognozowanie upadłości polskich przedsiębiorstw – porównanie skuteczności wybranych metod uczenia maszynowego oraz deep learningu

Poprawne przewidywanie niewypłacalności przedsiębiorstw jest niezwykle istotne z perspektywy zarządzania finansami przedsiębiorstw, gdyż ma ono kluczowe znaczenie w zarządzaniu należnościami, ocenie projektów inwestycyjnych, zarządzaniu kapitałem obrotowym, oceną zdolności do kontynuowania działania, podejmowaniu współpracy i podpisywaniu umów z innymi przedsiębiorstwami. Celem artykułu jest porównanie skuteczności wybranych algorytmów uczenia maszynowego i deep learningu, które zostały zastosowane na reprezentatywnej próbie polskich przedsiębiorstw z wykorzystaniem danych za lata 2008–2018. W artykule podjęto próbę porównania skuteczności następujących algorytmów machine learning (uczenia maszynowego): analizy dyskryminacyjnej (DA), funkcji logitowej (L), support vector machines (SVM), random forest (RF), gradient boosting decision trees (GB), sieci neuronowych z jedną warstwą ukrytą (NN), konwolucyjnych sieci neuronowych (CNN) oraz metody naïve Bayes (NB). Zgodnie z hipotezami badawczymi jeśli ma się dostęp do dużej próby firm, najskuteczniejszym algorytmem (pierwszym wyborem) w prognozie bankructwa są algorytmy: gradient boosting decision trees (H1), random forest (H2) i nierekurencyjne wielowarstwowe sieci neuronowe (H3). Wstępne hipotezy zostały sformułowane na podstawie opinii praktyków dotyczących przydatności różnych algorytmów uczenia maszynowego i algorytmów sztucznej inteligencji w prognozowaniu upadłości przedsiębiorstw. W artykule wykorzystano do uczenia algorytmów bardzo dużą (reprezentatywną) grupę przedsiębiorstw komercyjnych (dane za lata 2008–2013), a do walidacji skuteczności algorytmów również bardzo dużą populację przedsiębiorstw (dane za okres 2014–2018); obydwie populacje obejmowały zupełnie inne podmioty gospodarcze i inne okresy, co pozwoliło na rzetelne porównanie skuteczności badanych algorytmów.


Słowa kluczowe


prognozowanie upadłości, deep learning, uczenie maszynowe, finanse przedsiębiorstw

Pełny tekst

PDF (English)

Literatura


Aktan S. (2011), Application of Machine Learning Algorithms for Business Failure Prediction, “Investment Management and Financial Innovations”, vol. 8, no 2.

Alaminos D., del Castillo A., Fernandez M.Á. (2016), A Global Model for Bankruptcy Prediction, “PLoS One”, vol. 11, no 11, https://doi.org/10.1371/journal.pone.0166693.

Alfaro E., Garciá N., Gámez M., Elizondo D. (2008), Bankruptcy Forecasting: An Empirical Comparison of AdaBoost and Neural Networks, “Decision Support Systems”, vol. 45, no 1, https://doi.org/10.1016/j.dss.2007.12.002.

Altınırmak S., Karamaşa Ç. (2016), Comparison of Machine Learning Techniques for Analyzing Banks’ Financial Distress, “Balıkesir Üniversitesi Sosyal Bilimler Enstitüsü Dergisi”, vol. 19, no 36.

Anandarajan M., Lee P., Anandarajan A. (2001), Bankruptcy Prediction of Financially Stressed Firms: An Examination of the Predictive Accuracy of Artificial Neural Networks, “International Journal of Intelligent Systems in Accounting, Finance and Management”, vol. 10, no 2, https://doi.org/10.1002/isaf.199.

Arieshanti I., Purwananto Y., Ramadhani A., Nuha M. U., Ulinnuha N. (2013), Comparative Study of Bankruptcy Prediction Models, “Telkomnika”, vol. 11, no 3, https://doi.org/10.12928/telkomnika.v11i3.1143.

Barboza F., Kimura H., Altman E. (2017), Machine Learning Models and Bankruptcy Prediction, “Expert Systems with Applications”, vol. 83, no C, https://doi.org/10.1016/j.eswa.2017.04.006.

Blanco-Oliver A., Irimia-Dieguez A., Oliver-Alfonso M., Wilson N. (2015), Improving Bankruptcy Prediction in Micro-entities by Using Nonlinear Effects and Non-financial Variables, “Czech Journal of Economics and Finance”, vol. 65, no 2.

Brynjolfsson E., Mcafee A. (2017), The Business of Artificial Intelligence, “Harvard Business Review”, July.

Chaudhuri A., De K. (2011), Fuzzy Support Vector Machine for Bankruptcy Prediction, “Applied Soft Computing”, vol. 11, no 2, https://doi.org/10.1016/j.asoc.2010.10.003.

Chen M.-Y. (2012), Comparing Traditional Statistics, Decision Tree Classification and Support Vector Machine Techniques for Financial Bankruptcy Prediction, “Intelligent Automation and Soft Computing”, vol. 18, no 1, https://doi.org/10.1080/10798587.2012.10643227.

Cho S., Hong H., Ha B.-C. (2010), A Hybrid Approach Based on the Combination of Variable Selection Using Decision Trees and Case-based Reasoning Using the Mahalanobis Distance: For Bankruptcy Prediction, “Expert Systems with Applications”, vol. 37, no 4, https://doi.org/10.1016/j.eswa.2009.10.040.

Cho S., Kim J., Bae J. K. (2009), An Integrative Model with Subject Weight Based on Neural Network Learning for Bankruptcy Prediction, “Expert Systems with Applications”, vol. 36, no 1, https://doi.org/10.1016/j.eswa.2007.09.060.

Chuang C.-L. (2013), Application of Hybrid Case-based Reasoning for Enhanced Performance in Bankruptcy Prediction, “Information Sciences”, vol. 236, https://doi.org/10.1016/j.ins.2013.02.015.

Dellepiane U., Di Marcantonio M., Laghi E., Renzi S. (2015), Bankruptcy Prediction Using Support Vector Machines and Feature Selection during the Recent Financial Crisis, “International Journal of Economics and Finance”, vol. 7, no 8, https://doi.org/10.5539/ijef.v7n8p182.

Ecer F. (2013), Comparing the Bank Failure Prediction Performance of Neural Networks and Support Vector Machines: The Turkish Case, “Ekonomska Istraživanja – Economic Research”, vol. 26, no 3, https://doi.org/10.1080/1331677x.2013.11517623.

Edrogan B. E. (2013), Prediction of Bankruptcy Using Support Vector Machines: An Application to Bank Bankruptcy, “Journal of Statistical Computation and Simulation”, vol. 83, no 8, https://doi.org/10.1080/00949655.2012.666550.

Fedorova E., Gilenko E., Dovzhenko S. (2013), Bankruptcy Prediction for Russian Companies: Application of Combined Classifiers, “Expert Systems with Applications”, vol. 40, no 18, https://doi.org/10.1016/j.eswa.2013.07.032.

Gatnar E. (2008), Podejście wielomodelowe w zagadnieniach dyskryminacji i regresji [A multi-model approach to discrimination and regression problems], Wydawnictwo Naukowe PWN, Warszawa.

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”, vol. 241, no 1, https://doi.org/10.1016/j.ejor.2014.08.016.

Ghodselahi A., Amirmadhi A. (2011), Application of Artificial Intelligence Techniques for Credit Risk Evaluation, “International Journal of Modelling and Optimization”, vol. 1, no 3, https://doi.org/10.7763/ijmo.2011.v1.43.

Hauser R. P., Booth D. (2011), Predicting Bankruptcy with Robust Logistic Regression, “Journal of Data Science”, vol. 9.

Heo J., Yang J. Y. (2014), AdaBoost Based Bankruptcy Forecasting of Korean Construction Companies, “Applied Soft Computing”, vol. 24, https://doi.org/10.1016/j.asoc.2014.08.009.

Hu Y.-C., Tseng F.-M. (2007), Functional-link Net with a Fuzzy Integral for Bankruptcy Prediction, “Neurocomputing”, vol. 70, no 16–18, https://doi.org/10.1016/j.neucom.2006.10.111.

Jardin P. du (2009), Bankruptcy Prediction Models: How to Choose the Most Relevant Variables?, MPRA Paper, no 44380, MPRA, Munich.

Jayanthi J., Suresh J. K., Vaishnavi J. (2011), Bankruptcy Prediction Using SVM and Hybrid SVM Survey, “International Journal of Computer Applications”, vol. 34, no 7.

Kasgari A. A., Salehnezhad S. H., Ebadi F. (2013), The Bankruptcy Prediction by Neural Networks and Logistic Regression, “International Journal of Academic Research in Accounting, Finance and Management Sciences”, vol. 3, no 4.

Kim M.-J., Kang D.-K. (2010), Ensemble with Neural Networks for Bankruptcy Prediction, “Expert Systems with Applications”, vol. 37, no 4, https://doi.org/10.1016/j.eswa.2009.10.012.

Kim M-J., Kang D.-K. (2012), Classifiers Selection in Ensembles Using Genetic Algorithms for Bankruptcy Prediction, “Expert Systems with Applications”, vol. 39, no 10, https://doi.org/10.1016/j.eswa.2012.02.072.

Kim S. Y., Upneja A. (2014), Predicting Restaurant Financial Distress Using Decision Tree and AdaBoosted Decision Tree Models, “Economic Modelling”, vol. 36, https://doi.org/10.1016/j.econmod.2013.10.005.

Ko L.-J., Blocher E. J., Lin P. P. (2001), Prediction of Corporate Financial Distress: An Application of the Composite Rule Induction System, “The International Journal of Digital Accounting Research”, vol. 1, no 1, https://doi.org/10.4192/1577-8517-v1_4.

Korol T., Prusak B. (2009), Upadłość przedsiębiorstw a wykorzystywanie sztucznej inteligencji [Company insolvency and the use of artificial intelligence], CeDeWu, Warszawa.

Krichene A. (2017), Using a Naive Bayesian Classifier Methodology for Loan Risk Assessment: Evidence from a Tunisian Commercial Bank, “Journal of Economics, Finance and Administrative Science”, vol. 22, no 42, https://doi.org/10.1108/jefas-02-2017-0039.

Laitinen E. K., Laitinen T. (2000), Bankruptcy Prediction: Application of the Taylor’s Expansion in Logistic Regression, “International Review of Financial Analysis”, vol. 9, no 4, https://doi.org/10.1016/S1057-5219(00)00039-9.

Lee J., Jang D., Park S. (2017), Deep Learning-based Corporate Performance Prediction Model Considering Technical Capability, “Sustainability”, vol. 9, no 6, https://doi.org/10.3390/su9060899.

Lewis N. D. (2017), Machine Learning Made Easy with R: An Intuitive Step by Step Blueprint for Beginners, CreateSpace Independent Publishing Platform, New York.

Li H., Lee Y.-C., Zhou Y.-C., Sun J. (2011), The Random Subspace Binary Logit (RSBL) Model for Bankruptcy Prediction, “Knowledge-Based Systems”, vol. 24, no 8, https://doi.org/10.1016/j.knosys.2011.06.015.

Li H., Sun J. (2009), Majority Voting Combination of Multiple Case-based Reasoning for Financial Distress Prediction, “Expert Systems with Applications”, vol. 36, no 3, https://doi.org/10.1016/j.eswa.2008.05.019.

Li H., Sun J. (2010), Business Failure Prediction Using Hybrid2 Case-based Reasoning (H2CBR), “Computers and Operations Research”, vol. 37, no 1, https://doi.org/10.1016/j.cor.2009.04.003.

Li H., Sun J. (2011), Principal Component Case-based Reasoning Ensemble for Business Failure Prediction, “Information and Management”, vol. 48, no 6, https://doi.org/10.1016/j.im.2011.05.001.

Liao J.-J., Shih C.-H., Chen T.-F., Hsu M.-F. (2014), An Ensemble-based Model for Two-class Imbalanced Financial Problem, “Economic Modelling”, vol. 37, https://doi.org/10.1016/j.econmod.2013.11.013.

Marqués A. I., García V., Sánchez J. S. (2012), Exploring the Behaviour of Base Classifiers in Credit Scoring Ensembles, “Expert Systems with Applications”, vol. 39, no 11, https://doi.org/10.1016/j.eswa.2012.02.092.

Min J. H., Jeong C. (2009), A Binary Classification Method for Bankruptcy Prediction, “Expert Systems with Applications”, vol. 36, no 3, https://doi.org/10.1016/j.eswa.2008.06.073.

Min J. H., Lee Y.-C. (2005), Bankruptcy Prediction Using Support Vector Machine with Optimal Choice of Kernel Function Parameters, “Expert Systems with Applications”, vol. 28, no 4, https://doi.org/10.1016/j.eswa.2004.12.008.

Mirzaei M., Ramakrishnan S., Bekri M. (2016), Corporate Default Prediction with Industry Effects: Evidence from Emerging Markets, “International Journal of Economics and Financial Issues”, vol. 6, no 3S.

Nagaraj K., Sridhar A. (2015), A Predictive System for Detection of Bankruptcy Using Machine Learning Techniques, “International Journal of Data Mining and Knowledge Management Process”, vol. 5, no 1, https://doi.org/10.5121/ijdkp.2015.5103.

Nanni L., Lumini A. (2009), An Experimental Comparison of Ensemble of Classifiers for Bankruptcy Prediction and Credit Scoring, “Expert Systems with Applications”, vol. 36, no 2, https://doi.org/10.1016/j.eswa.2008.01.018.

Pawełek B., Grochowina D. (2017), Podejście wielomodelowe w prognozowaniu zagrożenia przedsiębiorstw upadłością w Polsce [The multiple-model approach in the prediction of company bankruptcy risk in Poland], „Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu”, no 468.

Peña T., Martínez S., Abudu B. (2009), Bankruptcy Prediction: A Comparison of Some Statistical and Machine Learning Techniques, Banco de México Working Papers, no 18, Banco de México, México.

Pociecha J., Pawełek B., Baryła M., Augustyn S. (2014), Statystyczne metody prognozowania bankructwa w zmieniającej się koniunkturze gospodarczej [Statistical methods of bankruptcy forecasting in a changing business environment], Fundacja Uniwersytetu Ekonomicznego w Krakowie, Kraków.

Ramakrishnan S., Mirzaei M., Naveed M. (2015), Corporate Bankruptcy Prediction: A Case of Emerging Economies, “International Journal of Sciences Basic and Applied Research”, vol. 19, no 1.

Shin K. S., Lee T. S., Kim H. J. (2005), An Application of Support Vector Machines in Bankruptcy Prediction Model, “Expert Systems with Applications”, vol. 28, no 1, https://doi.org/10.1016/j.eswa.2004.08.009.

Sun J., Jia M.-Y., Li H. (2011), AdaBoost Ensemble for Financial Distress Prediction: An Empirical Comparison with Data from Chinese Listed Companies, “Expert Systems with Applications”, vol. 38, no 8, https://doi.org/10.1016/j.eswa.2011.01.042.

Sun J., Li H. (2009), Financial Distress Prediction Based on Serial Combination of Multiple Classifiers, “Expert Systems with Applications”, vol. 36, no 4, https://doi.org/10.1016/j.eswa.2008.10.002.

Sun J., Li H. (2012), Financial Distress Prediction Using Support Vector Machines: Ensemble vs. Individual, “Applied Soft Computing”, vol. 12, no 8, https://doi.org/10.1016/j.asoc.2012.03.028.

Tsai C.-F. (2014), Combining Cluster Analysis with Classifier Ensembles to Predict Financial Distress, “Information Fusion”, vol. 16, https://doi.org/10.1016/j.inffus.2011.12.001.

Tsai C.-F., Cheng K.-C. (2012), Simple Instance Selection for Bankruptcy Prediction, “Knowledge-Based Systems”, vol. 27, https://doi.org/10.1016/j.knosys.2011.09.017.

Tseng F.-M., Hu Y.-C. (2010), Comparing Four Bankruptcy Prediction Models: Logit, Quadratic Interval Logit, Neural and Fuzzy Neural Networks, “Expert Systems with Applications”, vol. 37, no 3, https://doi.org/10.1016/j.eswa.2009.07.081.

West D., Dellana S., Qian J. (2005), Neural Network Ensemble Strategies for Financial Decision Applications, “Computers and Operations Research”, vol. 32, no 10, https://doi.org/10.1016/j.cor.2004.03.017.

Wyrobek J., Kluza K. (2018a), Efficiency of Gradient Boosting Decision Trees Technique in Polish Companies’ Bankruptcy Prediction (in:) Z. Wilimowska, L. Borzemski, J. Świątek (eds), Information Systems Architecture and Technology: Proceedings of 39th International Conference on Information Systems Architecture and Technology – ISAT 2018. Part 3, Springer, Cham.

Wyrobek J., Kluza K. (2018b), Efficiency of Random Decision Forest Technique in Polish Companies’ Bankruptcy Prediction (in:) L. Rutkowski, R. Scherer, M. Korytkowski, W. Pedrycz, R. Tadeusiewicz, J. M. Zurada (eds), Artificial Intelligence and Soft Computing. Part 2, Springer, Cham.

Xiao Z., Yang X., Pang Y., Dang X. (2011), The Prediction for Listed Companies’ Financial Distress by Using Multiple Prediction Methods with Rough Set and Dempster-Shafer Evidence Theory, “Knowledge-Based Systems”, vol. 26, https://doi.org/10.1016/j.knosys.2011.08.001.

Zhou L., Lai K. K., Yen J. (2014), Bankruptcy Prediction Using SVM Models with a New Approach to Combining Feature Selection and Parameter Optimization, “International Journal of Systems Science”, vol. 45, no 3, https://doi.org/10.1080/00207721.2012.720293.




DOI: https://doi.org/10.15678/ZNUEK.2018.0978.0603