Predicting Bankruptcy of Companies using Data Mining Models and Comparing the Results with Z Altman Model

Document Type : Original Article

Authors

1 Department of Accounting, Boroujerd Girls' Technical University, Lorestan, Iran (Corresponding author)

2 Department of Accounting, Payame Noor University, Nahavand, Hamadan, Iran

3 Department of Accounting, Kosar University of Bojnord, Bojnord, Iran

Abstract

One of the issues helping make investment decisions is appropriate tools and models to evaluate financial situation 0f the organization.  By means of these tools, investors can analyze financial situation of the organization and identify financial distress or an ideal condition, they become aware of making decisions to invest in appropriate conditions.  The main objective of this study is to evaluate the power of using data mining models which are among new tools of prediction.  This tool was used to predict the bankruptcy of companies listed in Tehran stock exchange and comparison the results with the Altman model as one of the prevalent methods of prediction the bankruptcy of a company. The research data includes information of all companies listed in Tehran stock exchange during the years 2013 to 2018 subjected to Title 141 of the law of trade and were bankrupt. Variables used in both models were five financial ratios. The data mining models on the average in the base year had a predictive ability of 92.4 percent and the Altman model had a predictive ability of 82.41 percent. Considering the results, it was shown that the data mining model has more power to predict bankruptcy.
 

Keywords

References

1)     Angga Pertapan, F, Sri Hartono, Dyah Purnomo WulanA. (2018). Bankruptcy Prediction in PT Blue Bird, Tbk 2011-2016 Using Altman Z-Score, Springate, and Zmijewski Model, The 2nd International Conference on Technology, Education, and Social Science. (The 2nd ICTESS 2018)
2)     Altman ,E.L,.(1968). Financail Ratios, Disarmament Analysis and the prediction of corporate Bankruptcy. the Journal of finance, 23(5) ,598-609
3)     Boyacioglu, M., Yakup ,K., Mer Kaan ,B. (2009).Predicting bank financial failures using neural networks, supportvector machines and multivariate statistical methods: A comparative analysis inthe sample of savings deposit insurance fund (SDIF) transferred banks inTurkey. Expert Systems with Applications, 36,3355–3366
4)     Firouzian .,M.,. Javid., D .,Najmodin, N. (2011).  Evaluation of application of models of predicting bankruptcy of Altman and the genetic algorithm in companies accepted in the Tehran stock exchange.  Accounting and Audit Reviews., 18( 65),99-114.
5)     Hung, chilhli. & Chen, jing-hong. (2007). A selective ensemble based on expected probabilities for bankruptcy prediction, Expert Systems with Applications, 36(3), 5297-5303
6)     GHodrati, H, Moghadam, A. (2010).The Accuracy of Bankruptcy Forecasting Models (Altman, Shirata, Fulmer, CI, Scheringite, Olson, Chemically, Genetic Frajzadeh and McKay Genetics) in Tehran Stock Exchange . Accounting and Audit Reviews, 16 (58) ,153-12.
7)     GHadirimoghadam, A; Gholampourfard, M; F Nasirzadeh, F. (2009). Review the ability of Altman and Olson bankruptcy prediction models to predict bankruptcy Companies listed on the Stock Exchange. Journal of Science and Development. 16(28), 100-125.
7) Karami, G; Seyyed Hosseini, S . (2012).The usefulness of accounting information to market information to predict bankruptcy. Accounting Knowledge, 3 (11), 93-116
8)     Kim, Myoung-Jong & Dae-Ki Kang. (2012) .  Classifiers selection in ensembles using genetic algorithms for bankruptcy prediction. Expert Systems with Applications, 15,  1-7.
9)     Jardin, Philippe Du & Eric Séverin. (2011). Predicting corporatebankruptcy using a self-organizing map: An empirical study to improvethe forecasting horizon of a financial failure model. Decision SupportSystems, 51: pp. 701–711
10)    Jeong ,Chulwoo, Jae  ، Min , H., Myung,  S. (2012). A tuning method for the architecture of neural network models incorporating GAM and GA as applied to bankruptcy prediction. Expert Systems with Applications, 39,3650–3658.
11)    Makiyan, N; Al-Mudarresi,S; Salim K. (2009). Comparison of artificial neural network with logistic regression and audit analysis in prediction companies bankruptcy. Quarterly Journal of Economic Research, (10) 10 , 141-161.
12)    Mehrani, S; Mehrani, K, Monasfi, Y; Karami , Gh. (2005) Applied research On Zimiski and Shirana 's prediction Pattern of bankruptcy in companies accepted in Tehran Stock Exchange. Accounting and auditing reviews. (12) 41, 105-131.
13)    Nakhaiezade, G. (1998). Data Mining, Theoretische Aspekte and Anwendungen Beiträge zur Wirtschaftsinformatik. Physica-Verlag.
14)    Premachandra, I. M., Bhabra, G. S. & Sueyoshi, T. (2009). DEA as a tool for bankruptcy assessment: A comparative study with logistic regression technique. European Journal of Operational Research, 193, 412-424
15)    Prusak, B.(2018). Review of Research into Enterprise BankruptcyPrediction in Selected Central and Eastern European Countries  International Journal of Financial Studies Review ,(6) 60,20-48
16)    Saffai, A. (2006). How to build a smart neural network? Example of object writing in artificial neural networks and artificial network. Network Monthly ,6 (71),9-87.
17)    Yoon, J,.Young, K. (2010). A practical approach tobankruptcy prediction for small businesses: Substitutingthe unavailablefinancial data for credit card sales information. Expert Systems with applicationWhitaker, R. (1999). The Early Stage of Financial Distress. Journal of Economics and Finance, 23 (2), 123-133
 
International Journal of Finance & Managerial Accounting
Volume 3, Issue 10
August 2018
Pages 33-46

Files

Share

How to cite

Statistics