Machine learning and decision support system on credit scoring

Abstract

Among the numerous alternatives used in the world of risk balance, it highlights the provision of guarantees in the formalization of credit agreements. The objective of this paper is to compare the achievement of fuzzy sets with that of artificial neural network-based decision trees on credit scoring to predict the recovered value using a sample of 1890 borrowers. Comparing with fuzzy logic, the decision analytic approach can more easily present the outcomes of the analysis. On the other hand, fuzzy logic makes some implicit assumptions that may make it even harder for credit-grantors to follow the logical decision-making process. This paper leads an initial study of collateral as a variable in the calculation of the credit scoring. The study concludes that the two models make modelling of uncertainty in the credit scoring process possible. Although more difficult to implement, fuzzy logic is more accurate for modelling the uncertainty. However, the decision tree model is more favourable to the presentation of the problem.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. 1.

    Akkoç S (2012) An empirical comparison of conventional techniques, neural networks and the three stage hybrid adaptive neuro fuzzy inference system (ANFIS) model for credit scoring analysis: the case of Turkish credit card data. Eur J Oper Res 222:168–178. https://doi.org/10.1016/j.ejor.2012.04.009

    Article  Google Scholar 

  2. 2.

    Lahsasna A, Ainon RN, Wah TY (2010) Credit scoring models using soft computing methods: a survey. Int Arab J Inf Technol 7:115–123

    Google Scholar 

  3. 3.

    Chen W, Xiang G, Liu Y, Wang K (2012) Credit risk evaluation by hybrid data mining technique. Syst Eng Procedia 3:194–200. https://doi.org/10.1016/j.sepro.2011.10.029

    Article  Google Scholar 

  4. 4.

    Ibn UF, Panford JK, Ben H-J (2014) Fuzzy logic approach to credit scoring for micro finances in Ghana (A case study of KWIQPLUS money lending). Int J Comput Appl 94(8):8887. https://doi.org/10.5120/16362-5772

    Article  Google Scholar 

  5. 5.

    Zamula A, Kavun S (2017) Complex systems modeling with intelligent control elements. Int J Model Simul Sci Comput 08:1750009. https://doi.org/10.1142/S179396231750009X

    Article  Google Scholar 

  6. 6.

    Abiyev RH (2014) Credit rating using type-2 fuzzy neural networks. Math Probl Eng. https://doi.org/10.1155/2014/460916

    MathSciNet  Article  MATH  Google Scholar 

  7. 7.

    Buikstra E, Fallon AB, Eley R (2007) A bi-level neural-based fuzzy classification approach for credit scoring problems. Rural Remote Health 7:543. https://doi.org/10.1002/cplx

    Article  Google Scholar 

  8. 8.

    Darwish NR, Abdelghany AS (2016) A fuzzy logic model for credit risk rating of Egyptian commercial banks. Int J Comput Sci Inf Secur 14:11–19

    Google Scholar 

  9. 9.

    Louzada F, Ara A, Fernandes GB (2016) Classification methods applied to credit scoring: a systematic review and overall comparison. Surv Oper Res Manag Sci 21:117–134. https://doi.org/10.1016/j.sorms.2016.10.001

    MathSciNet  Article  Google Scholar 

  10. 10.

    Mammadli S (2016) Fuzzy logic based loan evaluation system. Procedia Comput Sci 102:495–499. https://doi.org/10.1016/j.procs.2016.09.433

    Article  Google Scholar 

  11. 11.

    Rao TVN, Reddy K (2017) Application of fuzzy logic in financial markets for decision making. Int J Adv Res Comput Sci 8(3). https://doi.org/10.26483/ijarcs.v8i3.3020

  12. 12.

    Ye J (2017) Aggregation operators of trapezoidal intuitionistic fuzzy sets to multicriteria decision making. Int J Intell Inf Technol 13:1–22. https://doi.org/10.4018/IJIIT.2017100101

    Article  Google Scholar 

  13. 13.

    Ren S (2017) Multicriteria decision-making method under a single valued neutrosophic environment. Int J Intell Inf Technol 13:23–37. https://doi.org/10.4018/IJIIT.2017100102

    Article  Google Scholar 

  14. 14.

    Mohmad Hassim YM, Ghazali R (2013) Functional link neural network—artificial bee colony for time series temperature prediction. Springer, Berlin, pp 427–437

    Google Scholar 

  15. 15.

    Li EY (1994) Artificial neural networks and their business applications. Inf Manag 27:303–313. https://doi.org/10.1016/0378-7206(94)90024-8

    Article  Google Scholar 

  16. 16.

    Liao SH, Chu PH, Hsiao PY (2012) Data mining techniques and applications—a decade review from 2000 to 2011. Expert Syst Appl 39:11303–11311

    Article  Google Scholar 

  17. 17.

    Goonatilake S, Treleaven PC, Philip C (1995) Intelligent systems for finance and business. Wiley, Hoboken

    Google Scholar 

  18. 18.

    Bentley PJ, Kim J, Jung G-H, Choi J-U (2000) Fuzzy darwinian detection of credit card fraud. In: 14th Annual fall symposium of the Korean information processing society, vol 14

  19. 19.

    Hoffmann F, Baesens B, Martens J et al (2002) Comparing a genetic fuzzy and a neurofuzzy classifier for credit scoring. Int J Intell Syst 17:1067–1083. https://doi.org/10.1002/int.10052

    Article  MATH  Google Scholar 

  20. 20.

    Bojadziev G, Bojadziev M (2007) Fuzzy logic for business, finance, and management. World Scientific, Singapore

    Google Scholar 

  21. 21.

    Laha A (2007) Building contextual classifiers by integrating fuzzy rule based classification technique and k-nn method for credit scoring. Adv Eng Inform 21:281–291. https://doi.org/10.1016/j.aei.2006.12.004

    Article  Google Scholar 

  22. 22.

    Hájek P, Olej V (2015) Intuitionistic fuzzy neural network: the case of credit scoring using text information. Springer, Cham, pp 337–346

    Google Scholar 

  23. 23.

    Khashei M, Mirahmadi A (2015) A soft intelligent risk evaluation model for credit scoring classification. Int J Financ Stud 3:1–12

    Article  Google Scholar 

  24. 24.

    Malhotra R, Malhotra DK (2003) Evaluating consumer loans using neural networks. Omega 31:83–96. https://doi.org/10.1016/S0305-0483(03)00016-1

    Article  Google Scholar 

  25. 25.

    Kogut B, MacDuffie JP, Ragin C (2004) Prototypes and strategy: assigning causal credit using fuzzy sets. Eur Manag Rev 1:114–131. https://doi.org/10.1057/palgrave.emr.1500020

    Article  Google Scholar 

  26. 26.

    Ong C, Huang J, Tzeng G (2005) Building credit scoring models using genetic programming. Expert Syst Appl 29:41–47. https://doi.org/10.1016/j.eswa.2005.01.003

    Article  Google Scholar 

  27. 27.

    Dahal K, Hussain Z, Hossain MA (2005) Loan Risk analyzer based on fuzzy logic. In: 2005 IEEE international conference on e-technology, e-commerce and e-service. IEEE, pp 363–366

  28. 28.

    Jiao Y, Syau Y-R, Lee ES (2007) Modelling credit rating by fuzzy adaptive network. Math Comput Model 45:717–731. https://doi.org/10.1016/J.MCM.2005.11.016

    Article  MATH  Google Scholar 

  29. 29.

    Lahsasna A (2009) Evaluation of credit risk using evolutionary-fuzzy logic scheme. University of Malaya, Kuala Lumpur

    Google Scholar 

  30. 30.

    Wang S (2010) A comprehensive survey of data mining-based accounting-fraud detection research. In: 2010 international conference on intelligent computation technology and automation. IEEE, pp 50–53

  31. 31.

    Grace AM, Williams SO (2016) Comparative analysis of neural network and fuzzy logic techniques in credit risk evaluation. Int J Intell Inf Technol. https://doi.org/10.4018/IJIIT.2016010103

    Article  Google Scholar 

  32. 32.

    Sohn SY, Kim DH, Yoon JH (2016) Technology credit scoring model with fuzzy logistic regression. Appl Soft Comput 43:150–158. https://doi.org/10.1016/J.ASOC.2016.02.025

    Article  Google Scholar 

  33. 33.

    Paul U, Biswas A (2017) Consumer credit limit assignment using bayesian decision theory and fuzzy logic—a practical approach. J Manag 4:11–18

    Google Scholar 

  34. 34.

    Zurada J (2010) Could decision trees improve the classification accuracy and interpretability of loan granting decisions? In: 2010 43rd Hawaii international conference on system sciences. IEEE, pp 1–9

  35. 35.

    Rescher N (1969) Many-valued logic. McGraw-Hill, New York

    Google Scholar 

  36. 36.

    Zadeh LA (1965) Fuzzy sets. Inf Control 8:338–353. https://doi.org/10.1016/S0019-9958(65)90241-X

    Article  MATH  Google Scholar 

  37. 37.

    Baghban A, Jalali A, Shafiee M et al (2019) Developing an ANFIS-based swarm concept model for estimating the relative viscosity of nanofluids. Eng Appl Comput Fluid Mech 13:26–39. https://doi.org/10.1080/19942060.2018.1542345

    Article  Google Scholar 

  38. 38.

    Ohno-Machado L, Lacson R, Massad E (2000) Decision trees and fuzzy logic: a comparison of models for the selection of measles vaccination strategies in Brazil. In: Proceedings AMIA symposium, pp 625–629

  39. 39.

    Martens D, Baesens B, Van Gestel T, Vanthienen J (2007) Comprehensible credit scoring models using rule extraction from support vector machines. Eur J Oper Res 183:1466–1476. https://doi.org/10.1016/j.ejor.2006.04.051

    Article  MATH  Google Scholar 

  40. 40.

    Yaseen ZM, Sulaiman SO, Deo RC, Chau KW (2019) An enhanced extreme learning machine model for river flow forecasting: state-of-the-art, practical applications in water resource engineering area and future research direction. J Hydrol 569:387–408. https://doi.org/10.1016/j.jhydrol.2018.11.069

    Article  Google Scholar 

  41. 41.

    Wu DD, Olson DL (2014) A decision support approach for accounts receivable risk management. IEEE Trans Syst Man Cybern Syst 44:1624–1632. https://doi.org/10.1109/TSMC.2014.2318020

    Article  Google Scholar 

  42. 42.

    Massad E, Burattini MN, Ortega NR (1999) Fuzzy logic and measles vaccination: designing a control strategy. Int J Epidemiol 28:550–557

    Article  Google Scholar 

  43. 43.

    Zhang H, He H, Zhang W (2018) Classifier selection and clustering with fuzzy assignment in ensemble model for credit scoring. Neurocomputing 316:210–221. https://doi.org/10.1016/J.NEUCOM.2018.07.070

    Article  Google Scholar 

  44. 44.

    Yu L, Wang S, Lai KK (2009) An intelligent-agent-based fuzzy group decision making model for financial multicriteria decision support: the case of credit scoring. Eur J Oper Res 195:942–959. https://doi.org/10.1016/j.ejor.2007.11.025

    MathSciNet  Article  MATH  Google Scholar 

  45. 45.

    Freeling ANS (1980) Fuzzy sets and decision analysis. IEEE Trans Syst Man Cybern 10:341–354. https://doi.org/10.1109/TSMC.1980.4308515

    Article  Google Scholar 

  46. 46.

    Malhotra R, Malhotra DK (2002) Differentiating between good credits and bad credits using neuro-fuzzy systems. Eur J Oper Res 136:190–211. https://doi.org/10.1016/S0377-2217(01)00052-2

    Article  MATH  Google Scholar 

  47. 47.

    Hoffmann F, Baesens B, Mues C et al (2007) Inferring descriptive and approximate fuzzy rules for credit scoring using evolutionary algorithms. Eur J Oper Res 177:540–555. https://doi.org/10.1016/j.ejor.2005.09.044

    Article  MATH  Google Scholar 

  48. 48.

    Capotorti A, Barbanera E (2012) Credit scoring analysis using a fuzzy probabilistic rough set model. Comput Stat Data Anal 56:981–994. https://doi.org/10.1016/j.csda.2011.06.036

    MathSciNet  Article  MATH  Google Scholar 

  49. 49.

    Muslim MA, Nurzahputra A, Prasetiyo B (2018) Improving accuracy of C4.5 algorithm using split feature reduction model and bagging ensemble for credit card risk prediction. In: 2018 International conference on information and communications technology (ICOIACT). IEEE

  50. 50.

    Tang T-C, Chi L-C (2005) Predicting multilateral trade credit risks: comparisons of logit and fuzzy logic models using ROC curve analysis. Expert Syst Appl 28:547–556. https://doi.org/10.1016/J.ESWA.2004.12.016

    Article  Google Scholar 

  51. 51.

    Mierswa I, Wurst M, Klinkenberg R et al (2006) Yale: rapid prototyping for complex data mining tasks. In: Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining—KDD’06. ACM Press, New York, p 935

  52. 52.

    Huang JJ, Tzeng GH, Ong CS (2006) Two-stage genetic programming (2SGP) for the credit scoring model. Appl Math Comput 174:1039–1053. https://doi.org/10.1016/j.amc.2005.05.027

    MathSciNet  Article  MATH  Google Scholar 

  53. 53.

    Chen W, Ma C, Ma L (2009) Mining the customer credit using hybrid support vector machine technique. Expert Syst Appl 36:7611–7616. https://doi.org/10.1016/j.eswa.2008.09.054

    Article  Google Scholar 

  54. 54.

    Rahman N (2018) Data mining techniques and applications. Int J Strateg Inf Technol Appl 9:78–97. https://doi.org/10.4018/IJSITA.2018010104

    Article  Google Scholar 

  55. 55.

    Wang S, Li Y, Shao Y et al (2016) Detection of dendritic spines using wavelet packet entropy and fuzzy support vector machine. CNS Neurol Disord: Drug Targets 16:116–121. https://doi.org/10.2174/1871527315666161111123638

    Article  Google Scholar 

  56. 56.

    Zhang YD, Yang ZJ, Lu HM et al (2016) Facial emotion recognition based on biorthogonal wavelet entropy, fuzzy support vector machine, and stratified cross validation. IEEE Access 4:8375–8385. https://doi.org/10.1109/ACCESS.2016.2628407

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Funding from the FCT - Fundação para a Ciência e a Tecnologia through the UID/EEA/50008/2019 Project; by the Government of the Russian Federation, Grant 08-08; by Brazilian National Council for Research and Development (CNPq) via Grant No. 309335/2017-5; by Ciência sem Fronteiras of CNPq, Brazil, process number 200450/2015-8; and by the International Scientific Partnership Program ISPP at King Saud University through ISPP #0129.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Gernmanno Teles.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Teles, G., Rodrigues, J.J.P.C., Saleem, K. et al. Machine learning and decision support system on credit scoring. Neural Comput & Applic 32, 9809–9826 (2020). https://doi.org/10.1007/s00521-019-04537-7

Download citation

Keywords

  • Machine learning
  • Decision trees
  • Fuzzy logic
  • Credit scoring
  • Performance evaluation