TY - JOUR T1 - Öznitelik Seçim Yöntemleri ve Makine Öğrenmesi Kullanarak Şirket Bilanço Verilerine Dayalı İflas Riski Tahmini TT - Bankruptcy Risk Forecasting Based on Company Balance Sheet Data Using Feature Selection Methods And Machine Learning AU - Bulut, Necip AU - Shakeri, Saber AU - Yüzük, Seçil AU - Aktaş, Mehmet Sıddık PY - 2019 DA - December JF - Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi JO - TBV-BBMD PB - Akademik Bilişim Vakfı WT - DergiPark SN - 1305-8991 SP - 20 EP - 29 VL - 12 IS - 2 LA - tr AB - Bir şirketin başarısı hem firmanın içmuhatapları hem de yatırımcılar ve üçüncü kişilerce büyük önem taşımaktadır.Finansal olarak başarısızlık kimi zaman iflaslar ile sonuçlanabilmekte vefirmanın muhatapları üzerinde yıkıcı etkiler yaratabilmektedir. Yatırımcılar,finansörler, yöneticiler bazen de politika yapıcıları için firmaların iflasrisklerini tahmin etmek oldukça önemlidir. Literatürde iflas riskinin tahminiiçin birçok yöntem geliştirilse de Ohlson O-skoru ve Altman Z-skoru iflasriskini tahmin için oldukça sık kullanılan iki yöntemdir. Bu iki modelin hemlineer model olmaları hem de firmaların yalnızca son bilançolarıylailgilenmeleri bazen hatalı tahminlere yol açabilmektedir. İflas olgusunun birsüreç olduğu düşünüldüğünde şirketin sadece son finansal raporlarınınincelenmesi bir takım sakıncalar barındırır. Bu sebeple iflas risklerini doğrutahmin etmek için şirketlerin geçmiş finansal raporlarının da incelenmesigerekmektedir. Literatürdeki bu iki iflas riski tahmin yöntemi şirketlerinsadece son finansal raporlarıyla ilgilenmektedir. Ayrıca bu iki modeldeşirketin başarısına dair karar verilemeyen gri alanlar bulunmaktadır. Buçalışmada literatürdeki klasik lineer modeller yerine, lineer olmayan makineöğrenmesi algoritmaları kullanılarak şirketlerin iflas riskleri tahmin edilmeyeçalışılmıştır. Bu amaç doğrultusunda öznitelik seçim metodu olarak BilgiKazanımı ve Temel Bileşenler Analizi, Lineer Diskriminant Analizi ilebirleştirilerek ve makine öğrenmesi metodu olarak Lojistik Regresyon, KararDestek Vektörleri ve Rassal Orman algoritması kullanılmıştır. Bu bağlamdaşirketlerin iflas riskini makine öğrenmesi algoritmalarıyla tahmin etmenin,lineer klasik modellerden başarılı olduğu sonucuna ulaşılmıştır. KW - Ohlson O-skoru KW - Altman Z-Skoru KW - Şirket İflas Riski Tahmini KW - Öznitelik Çıkarımı KW - Makine Öğrenmesi N2 - The success of a company has a significant issue for both theinterlocutors of companies and other related persons. Financial failuresometimes end up bankrupt and can have a critical effect on the company’sinterlocutors. Prediction of bankruptcy is significant for investors, backers,directors and sometimes policymakers. Although there are a lot of models topredict bankruptcy in the financial literature, Ohlson O-score and AltmanZ-score are models that are used quite often. The fact that these twomodels are both linear models and companies are only interested in their latestbalance sheets can sometimes lead to incorrect predictions. Considering bankruptcy asa process, to interest in only the latest financial reports of the companieshas some drawbacks. For this reason, in addition to the current, previouslyfinancial reports of companies should be interested to predict bankruptcy riskof the company correctly. In the literature, these two classical modelsinterest in only the current financial reports of companies. Additionally,there are grey areas that are not decided about the bankruptcy of companies inthese two classical models. In thisstudy, it is tried to predict the bankruptcy risk of companies by usingnon-linear machine learning algorithms rather than classical linear models inthe financial literature. In line with this main purpose, as feature selectionmethods Information Gain, Principle Component Analysis algorithms by combiningLinear Discrimination Analysis algorithm and as machine learning methodsLogistic Regression, Support Vector Machine, and Random Forest algorithms areused. It has been found that predicting the bankruptcy risk of companies byusing non-linear machine learning algorithms is more successful than linearclassical models. CR - [1] Ohlson, James A. "Financial ratios and the probabilistic prediction of bankruptcy." Journal of accounting research ,1980, pp. 109-131 CR - [2] Altman, Edward I. "Financial ratios, discriminant analysis and the prediction of corporate bankruptcy." The journal of finance 23.4 , 1968, pp. 589-609 CR - [3] Taffler, Richard J. "Empirical models for the monitoring of UK corporations." Journal of Banking & Finance 8.2, 1984, pp. 199-227 CR - [4] Imelda, Elsa, and Ignacia Alodia. "The Analysis of Altman Model and Ohlson Model in Predicting Financial Distress of Manufacturing Companies in the Indonesia Stock Exchange." Indian-Pacific Journal of Accounting and Finance 1.1, 2017, pp. 51-63 CR - [5] Wang, Nanxi. "Bankruptcy prediction using machine learning." Journal of Mathematical Finance 7.04, 2017, pp. 908 CR - [6] Altaş, Dilek, and Selay Giray. "Mali Başarısızlığın Çok Değişkenli İstatistiksel Yöntemlerle Belirlenmesi: Tekstil Sektörü Örneği.", 2005 CR - [7] Muzir, Erol and Caglar, Nazan (2009), “The Accuracy of Financial Distress Prediction Models in Turkey: A Comparative Investigation with Simple Model Proposals”, Anadolu University Journal of Social Sciences, 9(2): 15-48 CR - [8] Raut, Sneha, Milind Tiwari, and Kuldeep Kumar. "Financial Distress Prediction Using Cutting-Edge Statistical Techniques: A Study of Australian Real Estate Sector." Shodh-Amrit: JKLU Journal of Engineering & Management 1.2, 2018, pp. 2-32 CR - [9] Viviani, Jean‐Laurent, and Hong LE Hanh. "Why Do Banks Fail?-The Explanation from Text Analytics Technique.", SSRN Electronic Journal, 2018 CR - [10] Lin, Wei‐Chao, Yu‐Hsin Lu, and Chih‐Fong Tsai. "Feature selection in single and ensemble learning‐based bankruptcy prediction models." Expert Systems 36.1, 2019, e12335 CR - [11] Vu, Loan Thi, et al. "Feature selection methods and sampling techniques to financial distress prediction for Vietnamese listed companies." Investment Management & Financial Innovations16.1, 2019, pp. 276 CR - [12] AKPINAR, Onur, and Gökçe AKPINAR. "Finansal Başarısızlık Riskinin Belirleyicileri: Borsa İstanbul’da Bir Uygulama.", Journal of Business Research – Turk, Volume 9, Issue 4 2017 CR - [13] Zeytinoglu, Emin, and Yasemin Deniz Akarim. "Financial failure prediction using financial ratios: An empirical application on Istanbul Stock Exchange." Journal of Applied Finance and Banking 3.3, 2013, pp. 107 CR - [14] Bellovary, Jodi L., Don E. Giacomino, and Michael D. Akers. "A review of bankruptcy prediction studies: 1930 to present." Journal of Financial education, 2007, pp. 1-42 CR - [15] Acosta-González, Eduardo, Fernando Fernández-Rodríguez, and Hicham Ganga. "Predicting corporate financial failure using macroeconomic variables and accounting data." Computational Economics 53.1, 2019, pp. 227-257 CR - [16] Chen, James Ming. "Models for Predicting Business Bankruptcies and Their Application to Banking and to Financial Regulation." Available at SSRN 3329147, 2019 CR - [17] Shakeri, S., & Ashouraei, M. (2016). NeurAda: Combining artificial neural network and Adaboost for accurate object detection. International Journal of Next-Generation Computing, 7(2), pp. 155-163 CR - [18] Christopoulos, Apostolos G., et al. "An implementation of Soft Set Theory in the Variables Selection Process for Corporate Failure Prediction Models. Evidence from NASDAQ Listed Firms." Bulletin of Applied Economics 6.1, 2019, pp. 1-20 CR - [19] Fernández, Manuel Ángel, et al. "Focused vs unfocused models for bankruptcy prediction: Empirical evidence for Spain." Contaduría y Administración 64.2, 2019, e96 CR - [20] Varatharajan, R., Manogaran, G., & Priyan, M. K. (2018). A big data classification approach using LDA with an enhanced SVM method for ECG signals in cloud computing. Multimedia Tools and Applications, 77(8), 10195-10215 CR - [21] Zengin T., Shakeri S., Bulut N., Yüzük1 S. and Aktaş M.S. (2019, September). Bankruptcy Risk Forecast Based on Company Balance Sheet Data Using Machine Learning. In 2019 4rd International Conference on Computer Science and Engineering (UBMK). IEEE. 2019 UR - https://dergipark.org.tr/tr/pub/tbbmd/issue//635899 L1 - https://dergipark.org.tr/tr/download/article-file/885999 ER -