It is well known that bankruptcy patterns are different across the industries, and consequently most studies focused on a given business sector or sub-sector. However, in some real world applications the bankruptcy patterns are likely constructed based on the companies of various business sectors (e.g. construction, real estate, education, retail, transportation) due to the lack of default samples. This paper presents a comparative study using different classifiers and performance metrics to examine the role of the business sector in corporate failure prediction based on the data from multiple business sectors. The experiments use a real-world French database of corporate companies diversified in different industries. The bankruptcy of companies is forecasted using 10 prediction models and evaluated by 8 performance metrics. The experimental results are analyzed by means of multidimensional scaling, which transforms the high dimensional metric data into a 2D space through a pairwise distance preserving projection. Through the interpretation of the results, we can find that the business sector used as a predictor significantly enhances the exploratory power of prediction models. Moreover, by analyzing the results there is evidence that not only tangible benefits are attained with business sector information but also the advanced ensemble approaches yield good to excellent improvements in this financial setting.
AhnH. and KimK.-J., Bankruptcy prediction modeling with hybrid case-based reasoning and genetic algorithms approach, Applied Soft Computing9(2) (2009), 599-607.
2.
Alaiz-RodriguezR., JapkowiczN. and TischerP., A visua- lization-based exploratory tool for classifier comparison with respect to multiple metrics and multiple domains, in: Proceedings of ECML PKDD, (2008), 660-665.
3.
BoyaciogluM.A., KaraY. and BaykanO.K., Predicting bank financial failures using neural networks, support vector machines and multivariate statistical methods: A comparative analysis in the sample of savings deposit insurance fund (SDIF) transferred banks in turkey, Expert Systems with Applications36 (2009), 3355-3366.
4.
BrockettP.L., GoldenL.L., JangJ. and YangC., A comparison of neural network, statistical methods, and variable choice for life insurers' financial distress prediction, The Journal of Risk and Insurance73(3) (2006), 397-419.
5.
CardwellP.M., McGregorC.C. and SynnW.J., Bankruptcy prediction in the textile industry, International Business & Economics Research Journal2(8) (2003), 31-40.
6.
CaruanaR. and Niculescu-MizilA., Data mining in metric space: An empirical analysis of suppervised learning performance criteria, in: Proceedings of the 10th International Conference on Knowledge Discovery and Data Mining, (2004).
7.
ChauhanN., RaviV. and ChandraD.K., Differential evolution trained wavelet neural networks: Application to bankruptcy prediction in banks, Expert Systems with Applications36(4) (2009), 7659-7665.
8.
ChaveS. and JarrowR.A., Bankruptcy prediction with industry effects, Review of Finance8(4) (2004), 537-569.
9.
ChenN., VieiraA.S., DuarteJ., RibeiroB. and NevesJ.C., A stable credit rating model based on learning vector quantization, Intelligent Data Analysis15(2) (2011), 237-250.
10.
ChoS., KimJ. and BaeJ.K., An integrative model with subject weight based on neural network learning for bankruptcy prediction, Expert Systems with Applications36(1) (2009), 403-410.
11.
DakovicR., CzadoC. and BergD., Bankruptcy prediction in norway: A comparison study, Applied Economics Letters17(17) (2010), 1739-1746.
12.
DemsarJ., Statistical comparisons of classifiers over multiple data sets, Journal of Machine Learning Research7 (2006), 1-30.
13.
EtemadiH., RostamyA.A.A. and DehkordiH.F., A genetic programming model for bankruptcy prediction: Empirical evidence from Iran, Expert Systems with Applications36(2) (2009), 3199-3207.
14.
GarcíaV., SánchezJ.S. and MollinedaR.A., On the effectiveness of preprocessing methods when dealing with different levels of class imbalance, Knowledge-Based Systems25 (2012), 13-21.
15.
GordiniN., A genetic algorithm approach for smes bank- ruptcy prediction: Empirical evidence from italy, Expert Systems with Applications41(41) (2014), 6433-6445.
16.
JapkowiczN., SanghiP. and TischerP., A projection-based framework for classifier performance evaluation, in: Proceedings of European Conference on Machine Learning and Knowledge Discovery in Databases-Part I, LNCS, Springer, Heidelberg 5211 (2008), 548-563.
17.
JeongC., MinJ.H. and KimM.S., A tuning method for the architecture of neural network models incorporating GAM and GA as applied to bankruptcy prediction, Expert Systems with Applications39(3) (2012), 3650-3658.
18.
LensbergT., EilifsenA. and McKeeT.E., Bankruptcy theory development and classification via genetic programming, European Journal of Operational Research169 (2006), 677-697.
19.
LiH. and SunJ., Forecasting business failure: The use of nearest-neighbour support vectors and correcting imbalanced samples - evidence from the Chinese hotel industry, Tourism Management33(3) (2012), 622-634.
20.
MinJ.H. and LeeY.-C., Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters, Expert Systems with Applications28 (2005), 603-614.
21.
United Nations, International Standard Industrial Classification of All Economic Activities (ISIC), revision 4 edition, New York, 2008.
NireshJ.A. and PratheepanT., The application of altman's z-score model in predicting bankruptcy: Evidence from the trading sector in sri lanka, International Journal of Business and Management10(12) (2015).
24.
OlsonD.L., DelenD. and MeangY., Comparative analysis of data mining methods for bankruptcy prediction, Decision Support Systems52(2) (2012), 464-473.
25.
KumarP.R. and RaviV., Bankruptcy prediction in banks and firms via statistical and intelligent techniques - a review, European Journal of Operational Research180(1) (July 2007), 1-28.
26.
RibeiroB., SilvaC., ChenN., VieiraA. and NevesJ.C., Enhanced default risk models with SVM+, Expert Systems with Applications39(11) (2012), 10140-10152.
27.
ShuangQ., YuanY., ZhangM. and YuD., Bankruptcy prediction in construction companies via fisher's linear discriminant analysis, in: 2011 International Conference on E-Business and E-Government (ICEE), (2011), 1-4.
28.
SueyoshiT. and GotoM., DEA-DA for bankruptcy-based performance assessment: Misclassification analysis of Japanese construction industry, European Journal of Operational Research199(2) (2009), 576-594.
29.
TsengF.-M. and HuY.-C., Comparing four bankruptcy prediction models: Logit, quadratic interval logit, neural and fuzzy neural networks, Expert Systems with Applications37(3) (2010), 1846-1853.
30.
TserngH.P., LinG.-F., TsaiL.K. and ChenP.-C., An enforced support vector machine model for construction contractor default prediction, Automation in Construction20(8) (2011), 1242-1249.
31.
WebbG.I., WellsJ. and ZhengZ., An experimental evaluation of integrating machine learning with knowledge acquisition, Machine Learning35(1) (1999), 5-23.
32.
WittenI.H., FrankE. and HallM.A., Data Mining: Practical Machine Learning Tools and Techniques, 3rd edition edition, Morgan Kaufmann, San Francisco, 2011.
33.
YangZ.R., PlattM.B. and PlattH.D., Probabilistic neural networks in bankruptcy prediction, Journal of Business Research2(44) (1999), 67-74.
34.
ZuradaJ. and LonialS., Comparison of the performance of several data mining methods for bad debt recovery in the healthcare industry, Journal of Applied Business Research21(2) (2005), 37-53.
