Financial distress prediction (FDP) has received considerable attention from both practitioners and researchers. This paper proposes a novel support vector machine (SVM) classifier ensemble framework based on earnings manipulation and fuzzy integral for FDP named SEMFI. We use financial data from the previous three years to predict companies’ current financial situation and divide the companies in each year into different categories according to whether they manipulate the earnings. Then, SVM is trained on different categories. The outputs of SVM are combined by fuzzy integral which adopts a new fuzzy measure determination method. This method considers the fact that recent financial data are more valuable for FDP. Additionally, when using the model trained by historical data for FDP, the external environment may have dramatically changed. Therefore, a fuzzy measure dynamic adjustment method is proposed by considering the confidence of each single classifier’s output, the consistency between each single classifier’s output and the diversity among classifiers. To verify the performance of SEMFI, an empirical study using real financial data is conducted. The results indicate that the introduction of earnings manipulation, the new fuzzy measure determination and dynamic adjustment method to FDP can significantly enhance the prediction performance.
Mendez-VazquezA.GaderP.KellerJ.M. et al., Minimum classification error training for choquet integrals with applications to landmine detection, Fuzzy Systems, IEEE Transactions on16 (2008), 225–238.
2.
VerikasA. and LipnickasA., Fusing neural networks through space partitioning and fuzzy integration, Neural Processing Letters16 (2002), 53–65.
3.
AbdallahA.C.B.FriguiH. and GaderP., Adaptive local fusion with fuzzy integrals, Fuzzy Systems, IEEE Transactions on20 (2012), 849–864.
4.
LauA.H.L., A five-state financial distress prediction model, Journal of Accounting Research (1987), 127–138.
5.
CortesC. and VapnikV., Support-vector networks, Machine Learning (1995), 273–297.
6.
ChangC.C. and LinC.J., LIBSVM: A library for support vector machines, Acm Transactions on Intelligent Systems & Technology2 (2011), 389–396.
7.
ChibelushiC.C.DeraviF. and MasonJ.S.D., Adaptive classifier integration for robust pattern recognition, Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on29 (1999), 902–907.
8.
ŠtefkaD. and HoleňaM., Dynamic classifier aggregation using interaction-sensitive fuzzy measures, Fuzzy Sets and Systems270 (2015), 25–52.
9.
SkalakD.B., The sources of increased accuracy for two proposed boosting algorithms, American Association for Artificial Intelligence, AAAI-96, Integrating Multiple Learned Models Workshop1129 (1996), 120–125.
10.
YeungD.S.WangX.Z. and TsangE.C.C., Handling interaction in fuzzy production rule reasoning, Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on34 (2004), 1979–1987.
11.
AltmanE.I., Financial ratios, discriminant analysis and the prediction of corporate bankruptcy, The Journal of Finance23 (1968), 589–609.
12.
ChenF.H.ChiD.J. and WangY.C., Detecting biotechnology industry’s earnings management using Bayesian network, principal component analysis, back propagation neural network, and decision tree, Economic Modelling46 (2015), 1–10.
13.
XiongG.ShiD.ChenJ. et al., Divisional fault diagnosis of large-scale power systems based on radial basis function neural network and fuzzy integral, Electric Power Systems Research105 (2013), 9–19.
14.
LiH.LiC.J.WuX.J. et al., Statistics-based wrapper for feature selection: An implementation on financial distress identification with support vector machine, Applied Soft Computing19 (2014), 57–67.
15.
LiH.SunJ.LiJ.C. and YanX.Y., Forecasting business failure using two-stage ensemble of multivariate discriminant analysis and logistic regression, Expert Systems30 (2013), 385–397.
16.
TserngH.P.LinG.F.TsaiL.K. and ChenP.C., An enforced support vector machine model for construction contractor default prediction, Automation in Construction20 (2011), 1242–1249.
17.
SunJ. and LiH., Data mining method for listed companies’ financial distress prediction, Knowledge-Based Systems21 (2008), 1–5.
18.
SunJ. and LiH., Financial distress prediction based on serial combination of multiple classifiers, Expert Systems with Applications36 (2009), 8659–8666.
19.
SunJ. and LiH., Financial distress prediction using support vector machines: Ensemble individualvs., Applied Soft Computing12 (2012), 2254–2265.
20.
SunJ. and LiH., Majority voting combination of multiple case-based reasoning for financial distress prediction, Expert Systems with Applications36 (2009), 4363–4373.
21.
SunJ. and HuiX.F., An application of support vector machine to companies’ financial distress prediction, Lecture Notes in Artificial Intelligence5 (2006), 274–282
22.
SunJ. and LiH., Listed companies’ financial distress prediction based on weighted majority voting combination of multiple classifiers, Expert Systems with Applications35 (2008), 818–827.
23.
BaeJ.K., Predicting financial distress of the South Korean manufacturing industries, Expert Systems with Applications39 (2012), 9159–9165.
24.
KuoJ.M.NingL. and SongX., The real and accrual-based earnings management behaviors: Evidence from the split share structure reform in China, The International Journal of Accounting49 (2014), 101–136.
25.
PolatK., Data weighting method on the basis of binary encoded output to solve multi-class pattern classification problems, Expert Systems with Applications40 (2013), 4637–4647.
26.
KimK.J. and ChoS.B., Fuzzy integration of structure adaptive SOMs for web content mining, Fuzzy Sets and Systems148 (2004), 43–60.
27.
PengL.ZhangH.YangB. et al., A new approach for imbalanced data classification based on data gravitation, Information Sciences288 (2014), 347–373.
28.
SiL.WangZ.TanC. et al., A novel approach for coal seam terrain prediction through information fusion of improved D-S evidence theory and neural network, Measurement54 (2014), 140–151.
29.
ChenL.H. and HsiaoH.D., Feature selection to diagnose a business crisis by using a real GA-based support vector machine: An empirical study, Expert Systems with Applications35 (2008), 1145–1155.
30.
SalchenbergerL.M.CinarE. and LashN.A., Neural networks: A new tool for predicting thrift failures, Decision Sciences23 (1992), 899–916.
31.
GrabischM. and LabreucheC., A decade of application of the Choquet and Sugeno integrals in multi-criteria decision aid, 4OR6 (2008), 1–44.
32.
GrabischM. and NicolasJ.M., Classification by fuzzy integral: Performance and tests, Fuzzy Sets and Systems65 (1994), 255–271.
33.
GrabischM., K-order additive discrete fuzzy measures and their representation, Fuzzy Sets and Systems92 (1997), 167–189.
34.
SugenoM., Theory of Fuzzy Integral and Its Application, Ph. D. Dissertation, Tokyo Institute of Technology, 1974.
35.
KimM.J. and KangD.K., Ensemble with neural networks for bankruptcy prediction, Expert Systems with Applications37 (2010), 3373–3379.
36.
KochiN. and WangZ., An algebraic method and a genetic algorithm to the identification of fuzzy measures based on Choquet integrals, Journal of Intelligent and Fuzzy Systems26 (2014), 1393–1400.
37.
PizziN.J. and PedryczW., Effective classification using feature selection and fuzzy integration, Fuzzy Sets and Systems159 (2008), 2859–2872.
38.
HealyP.M. and WahlenJ.M., A review of the earnings management literature and its implications for standard setting, Accounting Horizons13 (1999), 365–383.
39.
KumarP.R. and RaviV., Bankruptcy prediction in banks and firms via statistical and intelligent techniques-A review, European Journal of Operational Research180 (2007), 1–28.
40.
WuR.S., Predicting earnings management: A nonlinear approach, International Review of Economics & Finance30 (2014), 1–25.
41.
KothariS.P.LeoneA.J. and WasleyC.E., Performance matched discretionary accrual measures, Journal of Accounting and Economics39 (2005), 163–197.
42.
BellottiT. and CrookJ., Support vector machines for credit scoring and discovery of significant features, Expert Systems with Applications36 (2009), 3302–3308.
43.
GeW. and KimJ.B., Real earnings management and the cost of new corporate bonds, Journal of Business Research67 (2014), 641–647.
44.
LiW.WangD. and ChaiT., Flame image-based burning state recognition for sintering process of rotary kiln using heterogeneous features and fuzzy integral, Industrial Informatics, IEEE Transactions on8 (2012), 780–790.
45.
BeaverW.H., Alternative accounting measures as predictors of failure, Accounting Review (1968), 113–122.
46.
ChenX.WangX. and WuD.D., Credit risk measurement and early warning of SMEs: An empirical study of listed SMEs in China, Decision Support Systems49 (2010), 301–310.
47.
SongX.DingY.HuangJ. et al., Feature selection for support vector machine in financial crisis prediction: A case study in China, Expert Systems27 (2010), 299–310.
48.
CaoY., Aggregating multiple classification results using Choquet integral for financial distress early warning, Expert Systems with Applications39 (2012), 1830–1836.
49.
WangZ.LiW.LeeK.H. et al., Lower integrals and upper integrals with respect to nonadditive set functions, Fuzzy Sets and Systems159 (2008), 646–660.
50.
XiaoZ.YangX.NiuQ. et al., A new evaluation method based on d-s generalized fuzzy soft sets and its application in medical diagnosis problem, Applied Mathematical Modelling36 (2012), 4592–4604.
