Credit scoring is widely used by financial institutions for default prediction, however, a significant portion of online credit loan customers have inadequate or unverifiable credit histories, making it difficult for financial institutions to make effective credit decisions. Since the widespread use of smartphones and the popularity of mobile applications, it is worth investigating whether mobile application usage behaviors (App behaviors) of customers can effectively predict online loan defaults. This paper proposes a combined algorithm of CNN and LightGBM, and establishes credit scoring models with App behaviors to evaluate the default risk of online credit loans based on logistic regression, LightGBM, CNN and the combined algorithm, respectively. The experimental results suggest that App behaviors have an obvious effect on the default prediction of customers applying for online credit loans, and the combined model outperforms the other models in terms of the area under the curve (AUC). Furthermore, integrated credit scoring models are developed by combining App behaviors with traditional scoring features. A comparison of the integrated models and the traditional scoring model indicates that the integrated models have achieved a significant improvement in classification performance and App behaviors can be a powerful complement to the traditional credit scoring model.
ChiB.W. and HsuC.C., A hybrid approach to integrate genetic algorithm into dual scoring model in enhancing the performance of credit scoring model, Expert Systems with Applications39(3) (2012), 2650–2661.
2.
JonesS., JohnstoneD. and WilsonR., An empirical evaluation of the performance of binary classifiers in the prediction of credit ratings changes, Journal of Banking & Finance56 (2015), 72–85.
3.
AbdouH.A., TsafackM.D.D., NtimC.G. and BakerR.D., Predicting creditworthiness in retail banking with limited scoring data, Knowledge-Based Systems103 (2016), 89–103.
4.
NalicJ., MartinovicG. and ZagarD., New hybrid data mining model for credit scoring based on feature selection algorithm and ensemble classifiers, Advanced Engineering Informatics45 (2020), 101130.
5.
Demirgüç-KuntA., KlapperL., SingerD., AnsarS. and HessJ., The Global Findex Database 2017: Measuring Financial Inclusion and the Fintech Revolution, World Bank Group, Washington, (2018).
6.
OnayC. and ÖztürkE., A review of credit scoring research in the age of big data, Journal of Financial Regulation and Compliance26(3) (2018), 382–405.
7.
KvammeH., SellereiteN., AasK. and SjursenS., Predicting mortgage default using convolutional neural networks, Expert Systems with Applications102 (2018), 207–217.
8.
SpeakmanS., SridharanS. and MarkusI., Three Population Covariate Shift for Mobile Phone-Based Credit Scoring, Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies (2018), 1–7.
9.
TobbackE. and MartensD., Retail credit scoring using finegrained payment data, Journal of the Royal Statistical Society Series A-Statistics in Society182(4) (2019), 1227–1246.
10.
BergT., BurgV., GomboviA. and PuriM., On the rise of fintechs: Credit scoring using digital footprints, Social Science Electronic Publishing33(7) (2020), 2845–2897.
11.
NiuB., RenJ. and LiX., Credit scoring using machine learning by combing social network information: Evidence from peer-topeer lending, Information10(12) (2019), 397.
12.
KulkarniS.V. and DhageS.N., Advanced credit score calculation using social media and machine learning, Journal of Intelligent & Fuzzy Systems36(3) (2019), 2373–2380.
13.
DjeundjeV.B., CrookJ., CalabreseR. and HamidM., Enhancing credit scoring with alternative data, Expert Systems with Applications163 (2020), 113766.
14.
LiangK. and HeJ., Analyzing credit risk among Chinese P2Plending businesses by integrating text-related soft information, Electronic Commerce Research and Applications40 (2020), 100947.
15.
De CnuddeS., MoeyersomsJ., StankovaM., TobbackE., JavalyV. and MartensD., What does your facebook profile reveal about your creditworthiness? using alternative data for microfinance, Journal of the Operational Research Society70 (2018), 353–363.
16.
ÓskarsdóttirM., BravoC., SarrauteC., VanthienenJ. and BaesensB., The value of big data for credit scoring: Enhancing financial inclusion using mobile phone data and social network analytics, Applied Soft Computing74 (2019), 26–39.
17.
RoaL., Correa-BahnsenA., SuarezG., Cortés-TejadaF., LuqueM.A. and BravoC., Super-app behavioral patterns in credit risk models: Financial, statistical and regulatory implications, Expert Systems with Applications169 (2021), 114486.
18.
BlumenstockJ., Don’t forget people in the use of big data for development, Nature561(7722) (2018), 170–172.
19.
DurandD., Risk Elements in Consumer Instalment Financing, National Bureau of Economic Research, Inc., (1941), 189–201.
20.
WigintonJ.C., , A note on the comparison of logit and discriminant models of consumer credit behavior, The Journal of Financial Quantitative Analysis15 (1980), 757–770.
21.
KaoL.J., ChiuC.C. and ChiuF.Y., A bayesian latent variable model with classification and regression tree approach for behavior and credit scoring, Knowledge-Based Systems36 (2012), 245–252.
22.
LuoC., A comprehensive decision support approach for credit scoring, Industrial Management & Data Systems120(2) (2019), 280–290.
23.
SohnS.Y., KimD.H. and YoonJ.H., Technology credit scoring model with fuzzy logistic regression, Applied Soft Computing43 (2016), 150–158.
24.
ShenF., WangR. and ShenY., A cost-sensitive logistic regression credit scoring model based on multi-objective optimization approach, Technological and Economic Development of Economy26 (2019), 405429.
25.
SunJ., LiH., ChangP.C. and HuangQ.H., Dynamic credit scoring using b & b with incremental-SVM-ensemble, Kybernetes44 (2015), 518–535.
26.
MaldonadoS., BravoC., LopezJ. and PerezJ., Integrated framework for profit-based feature selection and SVM classification in credit scoring, Decision Support Systems104 (2017), 113–121.
27.
PawiakP., AbdarM. and AcharyaU.R., Application of new deep genetic cascade ensemble of SVM classifiers to predict the Australian credit scoring, Applied Soft Computing84 (2019), 105740.
Marcano-CedenoA., Marin-De-La-BarcenaA., Jimenez-TrilloJ., PinuelaJ.A. and AndinaD., Artificial metaplasticity neural network applied to credit scoring, International Journal of Neural Systems21(4) (2011), 311–317.
30.
VerikasA., GelzinisA. and BacauskieneM., Mining data with random forests: A survey and results of new tests, Pattern Recognition44(2) (2011), 330–349.
31.
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.
32.
ChenT. and GuestrinC., Xgboost:AScalableTree Boosting System, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD’16, San Francisco, California, USA, (2016), 785794.
33.
DastileX., CelikT. and PotsaneM., Statistical and machine learning models in credit scoring: A systematic literature survey, Applied Soft Computing91 (2020), 106263.
34.
KoutanaeiF.N., SajediH. and KhanbabaeiM., A hybrid data mining model of feature selection algorithms and ensemble learning classifiers for credit scoring, Journal of Retailing and Consumer Services27 (2015), 11–23.
35.
LiangL. and CaiX., Forecasting peer-to-peer platform default rate with LSTM neural network, Electronic Commerce Research and Applications43(8) (2020), 100997.
36.
LuoC., WuD. and WuD., A deep learning approach for credit scoring using credit default swaps, Engineering Applications of Artificial Intelligence65 (2017), 465–470.
37.
WeedD.L., Weight of evidence: A review of concept and methods, Risk analysis25(6) (2005), 1545–1557.
38.
RuizS., GomesP., RodriguesL. and GamaJ., Credit Scoring in Microfinance Using Non-traditional Data, in: Progress in Artificial Intelligence, Springer International Publishing, Cham, (2017), 447–458.
39.
KeG., MengQ., FinleyT., WangT., ChenW., MaW., YeQ. and LiuT.Y., Lightgbm: A Highly Efficient Gradient Boosting Decision Tree, in: Advances in Neural Information Processing Systems, Vol. 30, Curran Associates, Inc., (2017), 3146–3154.
40.
JinD., LuY., QinJ., ChengZ. and MaoZ., Swiftids: Real-time intrusion detection system based on lightgbm and parallel intrusion detection mechanism, Computers & Security97 (2020), 101984.
41.
LiY. and ChenW., A comparative performance assessment of ensemble learning for credit scoring, Mathematics8(10) (2020), 1756.
42.
ZengH., YangC., ZhangH., WuZ. and KongW., A LightGBM-Based EEG Analysis Method for Driver Mental States Classification, Computational Intelligence and Neuroscience2019(4) (2019), 1–11.
