Credit risk assessment plays a key role in determining the banking policies and commercial strategies of financial institutions. Ensemble learning approaches have been validated to be more competitive than individual classifiers and statistical techniques for default prediction. However, most researches focused on improving overall prediction accuracy rather than improving the identification of actual defaulted loans. In addition, model interpretability has not been paid enough attention in previous studies. To fill up these gaps, we propose a Multi-layer Multi-view Stacking Integration (MLMVS) approach to predict default risk in the P2P lending scenario. As the main innovation, our proposal explores multi-view learning and soft probability outputs to produce multi-layer integration based on stacking. An interpretable artificial intelligence tool LIME is embedded for interpreting the prediction results. We perform a comprehensive analysis of MLMVS on the Lending Club dataset and conduct comparative experiments to compare it with a number of well-known individual classifiers and ensemble classification methods, which demonstrate the superiority of MLMVS.
ChernobaiA.S.RachevS.T. and FabozziF.J., Operational risk: a guide to Basel II capital requirements, models, and analysis, Vol. 180, John Wiley & Sons, 2008.
2.
ChenD. and HanC., A comparative study of online P2P lending in the USA and China, Journal of Internet Banking and Commerce17(2) (2012), 1.
3.
HandD.J. and HenleyW.E., Statistical classification methods in consumer credit scoring: a review, Journal of the Royal Statistical Society: Series A (Statistics in Society)160(3) (1997), 523–541.
4.
NamvarA.SiamiM.RabhiF. and NaderpourM., Credit risk prediction in an imbalanced social lending environment, International Journal of Computational Intelligence Systems (2018).
5.
CaoP.LiuX.ZhangJ.ZhaoD.HuangM. and ZaianeO., 2, 1 norm regularized multi-kernel based joint nonlinear feature selection and over-sampling for imbalanced data classification, Neurocomputing234 (2017), 38–57.
6.
CrookJ.N.EdelmanD.B. and ThomasL.C., Recent developments in consumer credit risk assessment, European Journal of Operational Research183(3) (2007), 1447–1465.
7.
MarquésA.I.GarcíaV. and SánchezJ.S., Exploring the behaviour of base classifiers in credit scoring ensembles, Expert Systems with Applications39(11) (2012), 10244–10250.
8.
AbellánJ. and MantasC.J., Improving experimental studies about ensembles of classifiers for bankruptcy prediction and credit scoring, Expert Systems with Applications41(8) (2014), 3825–3830.
9.
WangG.MaJ.HuangL. and XuK., Two credit scoring models based on dual strategy ensemble trees, Knowledge-Based Systems26 (2012), 61–68.
10.
XiaoH.XiaoZ. and WangY., Ensemble classification based on supervised clustering for credit scoring, Applied Soft Computing43 (2016), 73–86.
11.
YuL.ZhouR.TangL. and ChenR., A DBN-based resampling SVM ensemble learning paradigm for credit classification with imbalanced data, Applied Soft Computing69 (2018), 192–202.
12.
ChenN.RibeiroB. and ChenA., Comparative study of classifier ensembles for cost-sensitive credit risk assessment, Intelligent Data Analysis19(1) (2015), 127–144.
13.
NiuK.ZhangZ.LiuY. and LiR., Resampling ensemble model based on data distribution for imbalanced credit risk evaluation in P2P lending, Information Sciences536 (2020), 120–134.
14.
ShenF.ZhaoX.KouG. and AlsaadiF.E., A new deep learning ensemble credit risk evaluation model with an improved synthetic minority oversampling technique, Applied Soft Computing98 (2021), 106852.
15.
SongY.WangY.YeX.WangD.YinY. and WangY., Multi-view ensemble learning based on distance-to-model and adaptive clustering for imbalanced credit risk assessment in P2P lending, Information Sciences525 (2020), 182–204.
16.
JohnsonJ. and Giraud-CarrierC., Diversity, accuracy and efficiency in ensemble learning: An unexpected result, Intelligent Data Analysis23(2) (2019), 297–311.
17.
CamposR.CanutoS.SallesT.de SáC.C. and GonçalvesM.A., Stacking bagged and boosted forests for effective automated classification, in: Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval, 2017, pp. 105–114.
18.
AmasyaliM.F., Improved space forest: A meta ensemble method, IEEE Transactions on Cybernetics49(3) (2018), 816–826.
19.
BhowanU.JohnstonM.ZhangM. and YaoX., Evolving diverse ensembles using genetic programming for classification with unbalanced data, IEEE Transactions on Evolutionary Computation17(3) (2012), 368–386.
20.
XiaY.ZhaoJ.HeL.LiY. and NiuM., A novel tree-based dynamic heterogeneous ensemble method for credit scoring, Expert Systems with Applications159 (2020), 113615.
21.
NalićJ.MartinovićG. and ŽagarD., New hybrid data mining model for credit scoring based on feature selection algorithm and ensemble classifiers, Advanced Engineering Informatics45 (2020), 101130.
22.
TripathiD.EdlaD.R.CherukuR. and KuppiliV., A novel hybrid credit scoring model based on ensemble feature selection and multilayer ensemble classification, Computational Intelligence35(2) (2019), 371–394.
23.
XiaY.LiuC.DaB. and XieF., A novel heterogeneous ensemble credit scoring model based on bstacking approach, Expert Systems with Applications93 (2018), 182–199.
24.
XieX.PangS. and ChenJ., Hybrid recommendation model based on deep learning and Stacking integration strategy, Intelligent Data Analysis24(6) (2020), 1329–1344.
25.
HsiehN.-C. and HungL.-P., A data driven ensemble classifier for credit scoring analysis, Expert Systems with Applications37(1) (2010), 534–545.
26.
TomczakJ.M. and ZiębaM., Classification restricted Boltzmann machine for comprehensible credit scoring model, Expert Systems with Applications42(4) (2015), 1789–1796.
27.
VisaniG.BagliE.ChesaniF.PoluzziA. and CapuzzoD., Statistical stability indices for LIME: Obtaining reliable explanations for machine learning models, Journal of the Operational Research Society73(1) (2022), 91–101.
28.
JadhavS.HeH. and JenkinsK., Information gain directed genetic algorithm wrapper feature selection for credit rating, Applied Soft Computing69 (2018), 541–553.
29.
ZhaoJ.XieX.XuX. and SunS., Multi-view learning overview: Recent progress and new challenges, Information Fusion38 (2017), 43–54.
30.
WrightR.E., Logistic regression, American Psychological Association (1995).
TaudH. and MasJ., Multilayer perceptron (MLP), Geomatic approaches for modeling land change scenarios (2018), 451–455.
33.
MylesA.J.FeudaleR.N.LiuY.WoodyN.A. and BrownS.D., An introduction to decision tree modeling, Journal of Chemometrics: A Journal of the Chemometrics Society18(6) (2004), 275–285.
34.
RigattiS.J., Random forest, Journal of Insurance Medicine47(1) (2017), 31–39.
35.
ChenT.HeT.BenestyM.KhotilovichV.TangY.ChoH.ChenK., Xgboost: extreme gradient boosting, R package version 0.4-21(4) (2015), 1–4.
36.
KeG.MengQ.FinleyT.WangT.ChenW.MaW.YeQ. and LiuT.-Y., Lightgbm: a highly efficient gradient boosting decision tree, Advances in neural information processing systems30 (2017).
37.
FengX.XiaoZ.ZhongB.QiuJ. and DongY., Dynamic ensemble classification for credit scoring using soft probability, Applied Soft Computing65 (2018), 139–151.
38.
RibeiroM.T.SinghS. and GuestrinC., “Why should i trust you?” Explaining the predictions of any classifier, in: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, pp. 1135–1144.
39.
DurandD., Risk elements in consumer installment financing, National Bureau of Economic Research, New York, 1941.
40.
OrglerY.E., A credit scoring model for commercial loans, Journal of Money, Credit and Banking2(4) (1970), 435–445.
41.
WigintonJ.C., A note on the comparison of logit and discriminant models of consumer credit behavior, Journal of Financial and Quantitative Analysis15(3) (1980), 757–770.
42.
SteenackersA. and GoovaertsM., A credit scoring model for personal loans, Insurance: Mathematics & Economics8(1) (1989), 31–34.
43.
TsaiC.-F. and ChenM.-L., Credit rating by hybrid machine learning techniques, Applied Soft Computing10(2) (2010), 374–380.
TibshiraniR.J. and EfronB., An introduction to the bootstrap, Monographs on Statistics and Applied Probability57 (1993), 1–436.
46.
LiC.HuangY.Y.YouD.C. and ManagementS.O., Application on Individual Credit Score for Bank of a Boosting-based Ensemble Learning Algorithm, Value Engineering (2017).
47.
AbdouH.PointonJ. and El-MasryA., Neural nets versus conventional techniques in credit scoring in Egyptian banking, Expert Systems with Applications35(3) (2008), 1275–1292.
48.
LessmannS.BaesensB.SeowH.-V. and ThomasL.C., Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research, European Journal of Operational Research247(1) (2015), 124–136.
49.
Boiko FerreiraL.E.BarddalJ.P.GomesH.M. and EnembreckF., Improving Credit Risk Prediction in Online Peer-to-Peer (P2P) Lending Using Imbalanced Learning Techniques, in: 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI), 2017, pp. 175–181. doi: 10.1109/ICTAI.2017.00037.
50.
HastieT.TibshiraniR.FriedmanJ.H. and FriedmanJ.H., The elements of statistical learning: data mining, inference, and prediction, Vol. 2, Springer, 2009.
51.
TwalaB., Multiple classifier application to credit risk assessment, Expert Systems with Applications37(4) (2010), 3326–3336.
52.
DaubieM.LevecqP. and MeskensN., A comparison of the rough sets and recursive partitioning induction approaches: An application to commercial loans, International Transactions in Operational Research9(5) (2002), 681–694.
53.
WuX.YangY. and RenL., Entropy difference and kernel-based oversampling technique for imbalanced data learning, Intelligent Data Analysis24(6) (2020), 1239–1255.
54.
TzortzisG. and LikasA., Kernel-based weighted multi-view clustering, 2012 IEEE 12th international conference on data mining (2012), 675–684.
