This work addresses the problem of knowledge extraction within the banking domain using statistical learning systems. Our main goal is to assess the power of the accounting ratios to discriminate between Islamic, mixed and conventional banks in the Gulf Cooperation Council (GCC) region. To this end, we have used the two popular statistical learning methods, namely Support Vector Machines (SVM) and Random Forests (RF). An intensive comparative study is performed between them for the purpose of variable ranking and selection within a nonlinear multiclass framework. The experiments conducted on different simulated datasets and on the real dataset show that RF are slightly better than SVM.
In the real application, we had recourse to the financial semantics based on experts' domain knowledge to decide between the competitive approaches. The results show the importance of the mutual financial information between some ratios to distinguish between the three categories of banks. Moreover, we have demonstrated that mixed banks are more akin to conventional ones. Finally, it was shown that RF are more robust to the selection bias problem and classification accuracy is slightly improved by the ratios selection.
AllweinE.L., SchapireR.E. and SingerY., Reducing multiclass to binary: A unifying approach for margin classifiers, Journal of Machine Learning Research1 (2000), 113-141.
2.
AmaldiE. and KannV., On the approximability of minimizing non zero variables or unsatisfied relations in linear systems, Theoretical Computer Science209(1-2) (1998), 237-260.
3.
AmbroiseC. and McLachlanG.J., Selection bias in gene extraction on the basis of microarray gene-expression data, National Academy of Sciences99(10) (2002), 6562-6566.
4.
AnandarajanA., HasanI. and McCarthyC., Use of loan loss provisions for capital, earnings management and signaling by Australian banks, Accounting and Finance47 (2007), 357-379.
5.
BeckT., Demirgüç-KuntA. and MerroucheO., Islamic vs. conventional banking: Business model, efficiency and stability, Journal of Banking and Finance37(2) (2013), 433-447.
6.
IshakA.B., Sélection de variables par les machines à vecteurs supports pour la discrimination binaire et multiclasse en grande dimension, Ph.D. diss., Université de la Mé diterranée, Marseille, France, 2007.
7.
IshakA.B. and GhattasB., An efficient method for variable selection using svm-based criteria, preprint IML (2005), l'Institut de Mathématiques de Luminy, Marseille, France. Available at http://iml.univ-mrs.fr/editions/preprint2005/ preprint2005.html.
8.
IshakA.B., Variable selection using support vector regression and random forests: A comparative study, To appear in Intelligent Data Analysis20(1) (2016).
9.
OthmanH.B. and MersniH., The use of discretionary loan loss provisions by Islamic banks and conventional banks in the Middle East region: A comparative study, Studies in Economics and Finance31 (2014), 106-128.
10.
BhattiI. and MismanF.N., Risks exposure in Islamic banks: A case study of Bank Islam Malaysia Berhad (BIMB), Australian Center for Financial Studies, Finsia Banking and Finance Conference, (2010).
11.
BoserB.E., GuyonI.M and VapnikV.N., A training algorithm for optimal margin classifiers, in: Proceedings of the Fifth Annual Workshop on Computational Learning Theory COLT '92, New York, NY, USA: ACM Press, Pittsburgh, (1992), 144-152.
BreimanL., Random forests, Machine Learning45 (2001), 5-32.
14.
BreimanL., FriedmanJ.H., OlshenR.A. and StoneC.J., Classification and Regression Trees, Wadsworth and Brooks, 1984.
15.
ChapraM.U., The global financial crisis: Can Islamic finance help? Journal of Economics and Management16(2) (2009), 111-138.
16.
ChenY.-S., Classifying credit ratings for Asian banks using integrating feature selection and the CPDA-based rough sets approach, Knowledge-Based Systems26 (2012), 259-270.
17.
DarH.A. and PreselyR., Lack of profit loss sharing in Islamic banking: Management and control imbalances, Economic research paper N° 00/24, Department of Economics, Loughborough University, 2000.
18.
DietterichT.G. and BakiriG., Solving multiclass learning problems via error-correcting output codes, Journal of Artificial Intelligence Research2 (1995), 263-286.
19.
Díaz-UriarteR. and de AndrésS.A., Gene selection and classification of microarray data using random forest, BMC Bioinformatics7(3) (2006).
20.
DudaR.O., HartP.E. and StorkD.G., Pattern Classification, Wiley, New York, 2001.
21.
El-GamalM., Islamic Finance, Law, Economics, and Practice, Cambridge: Cambridge University Press, 2006.
22.
ElnahassM., IzzeldinM. and AbdelsalamO., Loan loss provisions, bank valuations and discretion: A comparative study between conventional and Islamic banks, Journal of Economic Behavior and Organization103 (2014), 160-173.
23.
ErdoganB.E., Prediction of bankruptcy using support vector machines: An application to bank bankruptcy, J Stat Comp Sim83 (2013), 1543-1555.
24.
FekiA., IshakA.B. and FekiS., Feature selection using bayesian and multiclass support vector machines approaches: Application to bank risk prediction, Expert Systems with Applications39(3) (2012), 3087-3099.
25.
GenuerR., PoggiJ.-M. and TuleauC., Variable selection using random forests, Pattern Recognition Letters31 (2010), 2225-2236.
26.
GhattasB. and IshakA.B., Sélection de variables pour la classification binaire en grande dimension: Comparaisons et application aux données de biopuces, Journal de la Société Française de Statistiques149(3) (2008), 43-66.
27.
GuermeurY., A generic model of multi-class support vector machine, International Journal of Intelligent Information and Database Systems6(6) (2012), 555-577.
28.
GuermeurY., VC theory of large margin multi-category classifiers, Journal of Machine Learning Research8 (2007), 2551-2594.
29.
GuyonI. and ElisseeffA., An introduction to variable and feature selection, Journal of Machine Learning Research3 (2003), 1157-1182.
30.
HajekP. and MichalakK., Feature selection in corporate credit rating prediction, Knowledge-Based Systems51 (2013), 72-84.
31.
JohnesJ., IzzeldinM. and PappasV., A comparison of performance of Islamic and conventional banks 2004-2009, Journal of Economic Behavior and Organization103 (2014), 93-107.
32.
Kreß elU.H.-G., Pairwise Classification and Support Vector Machines, in Advances in Kernel Methods: Support Vector Learning, Cambridge, MA, USA: MIT Press, 1999, pp. 255-268.
33.
LiangD., TsaiC.-F. and WuH.-T., The effect of feature selection on financial distress prediction, Knowledge-Based Systems73 (2015), 289-297.
34.
LinF., LiangD., YehC.-C. and HuangJ.-C., Novel feature selection methods to financial distress prediction, Expert Systems with Applications41 (2014), 2472-2483.
35.
OlsonD. and ZoubiT.A., Using accounting ratios to distinguish between Islamic and conventional banks in the GCC region, The International Journal of Accounting43 (2008), 45-65.
36.
OrsenigoC. and VercellisC., Linear versus nonlinear dimensionality reduction for banks' credit rating prediction, Knowledge-Based Systems47 (2013), 14-22.
37.
PhetkaewT., KijsirikulB. and RivepiboonW., Reordering adaptive directed acyclic graphs for multiclass support vector machines, in: Proceedings of the Third International Conference on Intelligent Technologies, (2002).
38.
RakotomamonjyA., Variable selection using SVM-based criteria, Journal of Machine Learning Research3 (2003), 1357-1370.
39.
SamadA. and HassanK., The performance of Malaysian Islamic bank during 1984-1997: An exploratory study, International Journal of Islamic Financial Services1 (1999), 1-14.
40.
SiddiqiM.N., Issues in Islamic banking, The Islamic Foundation, Leicester, UK, 1983.
41.
TsaiC.-F., Feature selection in bankruptcy prediction, Knowledge-Based Systems22(2) (2009), 120-127.
42.
TurenS., Performance and risk analysis of the Islamic banks: The case of Bahrain Islamic bank, Journal of King Abdulaziz University: Islamic Economics8 (1996), 3-14.
43.
VapnikV.N., Statistical Learning Theory, Wiley, New York, 1998.
44.
VapnikV.N., The Nature of Statistical Learning Theory, Springer Verlag, New York, 1995.
45.
VapnikV.N. and ChapelleO., Bounds on error expectation for support vector machines, Neural Computation12(9) (2000), 2013-2036.
46.
WestonJ., MukherjeeS., ChapelleO., PontilM., PoggioT. and VapnikV., Feature selection for SVMs, in: Neural Information Processing Systems13 (2000).
47.
WidagdoA.K. and IkaS.R., The interest prohibition and financial performance of islamic banks: Indonesian evidence, International Business Research1(3) (2008), 98-109.
48.
ZhuJ., ZouH., RossetS. and HastieT., Multi-class AdaBoost, Statistics and its Interface2 (2009), 349-360.
