Abstract
Credit scoring is important for credit risk evaluation and monitoring in the accounting and finance domain. For financial institutions, the ability to predict the business failure is crucial, as incorrect decisions have direct financial consequences. A variety of pattern recognition techniques including neural networks, decision trees, and support vector machines have been applied to predict whether the borrowers should be considered a good or bad credit risk. This paper presents a hybrid approach to building the credit scoring model and illustrates how the unsupervised learning based on self-organizing map (SOM) can improve the discriminant capability of feedforward neural network (FNN). Within the hybridization scheme, the knowledge (i.e., prototypes of clusters) found by SOM is transferred as input to the subsequent FNN model. Four real-world data sets are used in the experiments for credit approval problems. By varying the parameters, the experimental results demonstrate the predictive model built by the hybrid approach can achieve better performance than the stand-alone FNN particularly when a limited amount of labeled data is available. This gives some insights on how to construct more accurate predictive models when the data collection is difficult in some financial applications. A complete and unique graphical visualization technique is shown which better outlines the trade-off between distinct metrics and attained performance.
Similar content being viewed by others
References
Atiya AF (2001) Bankruptcy prediction for credit risk using neural networks: a survey and new results. IEEE Trans Neural Netw 12(4):929–935
Bapat V, Nagale A (2014) Comparison of bankruptcy prediction models: evidence from india. Account Finance Res 3(4):91–98
Burda A, Pancerz K (2014) Clustering and visualization of bankruptcy patterns using the self-organizing maps. Barometr Regionalny 12(3):133–138
Chen N, Ribeiro B, Vieira A, Chen A (2013) Clustering and visualization of bankruptcy trajectory using self-organizing map. Expert Syst Appl 40(1):385–393
Davidian D (1995) Feed-forward neural network. US, US 5438646 A
Dharamkar B, Singh RR (2014) A review of cyber attack classification technique based on data mining and neural network approach. Int J Comput Trends Technol 7(2):100–105
Dietterich TG, Bakiri G (1995) Solving multiclass learning problems via error-correcting output codes. J Artif Intell Res 2(2):263–286
Dreiseitl S, Ohno-Machado L (2002) Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform 35(5–6):352–359
Greene WH (1992) A statistical model for credit scoring. Technical Report EC-92-29, NYU Working Paper
Harris T (2015) Credit scoring using the clustered support vector machine. Expert Syst Appl 42(2):741–750
Huang Z, Chen H, Hsu CJ, Chen WH, Wu S (2010) Credit rating analysis with support vector machines and neural networks: a market comparative study. Decis Support Syst 37(4):543–558
Japkowicz N (2002) Supervised learning with unsupervised output separation. In: International conference on artificial intelligence and soft computing, pp 321–325
Kalinic H, Mihanovic H, Cosoli S, Vilibic I (2015) Sensitivity of self-organizing map surface current patterns to the use of radial vs. cartesian input vectors measured by high-frequency radars. Comput Geosci 84:29–36
Karem F, Dhibi M, Martin A (2012) Combination of supervised and unsupervised classification using the theory of belief functions. Springer, Berlin
Khashman A (2010) Neural networks for credit risk evaluation: investigation of different neural models and learning schemes. Expert Syst Appl 37(9):6233–6239
Kohonen T SOM toolbox. Technical report, Laboratory of computer and information sciences and Neural networks research center, Helsinki University of Technology. http://www.cis.hut.fi/projects/somtoolbox/
Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43:59–69
Lichman M (2013) UCI machine learning repository. Technical report, University of California, Irvine, School of Information and Computer Sciences. http://archive.ics.uci.edu/ml
Lin WY, Hu YH, Fong TC (2012) Machine learning in financial crisis prediction: a survey. IEEE Trans Syst Man Cybern Part C Appl Rev 42(4):421–436
Mahmon NA, Ya’acob N (2014) A review on classification of satellite image using artificial neural network (ANN). In: 2014 IEEE 5th control and system graduate research colloquium (ICSGRC), pp 153–157
Pandey M, Pandey AK, Mishra A, Tripathi BD (2015) Application of chemometric analysis and self organizing map-artificial neural network as source receptor modeling for metal speciation in river sediment. Environ Pollut 204:64–73
Silva C, Ribeiro B (2016) Multiclass ensemble of one-against-all SVM classifier. In: International symposium on neural networks (ISNN), LNCS, Russia
Merkevicius E, Garsva G, Simutis R (2004) Forecasting of credit classes with the self-organizing maps. Inf Technol Control 33(4):61–66
Tamura M, Kitamura N, Watarai S (2016) Artificial neural networks in business: two decades of research. Appl Soft Comput 38:788–804
Thomas LC (2000) A survey of credit and behavioural scoring: forecasting financial risk of lending to consumers. Int J Forecast 16(2):149–172
Torresani L (2014) Weakly supervised learning. Springer, New York
Tsai CF, Wu JW (2008) Using neural network ensembles for bankruptcy prediction and credit scoring. Expert Syst Appl 34(4):2639–2649
Verikas A, Kalsyte Z, Bacauskiene M, Gelzinis A (2010) Hybrid and ensemble-based soft computing techniques in bankruptcy prediction: a survey. Soft Comput A Fusion Found Methodol Appl 14(9):995–1010
Vieira JC, Neves A (2006) Improving bankruptcy prediction with hidden layer learning vector quantization. Eur Account Rev 15(15):253–271
Yap BW, Ong SH (2011) Using data mining to improve assessment of credit worthiness via credit scoring models. Expert Syst Appl 38(10):13274–13283
Yu L, Wang S, Lai KK (2008) Credit risk assessment with a multistage neural network ensemble learning approach. Expert Syst Appl 34(2):1434–1444
Zeng X, Li Y, He R, Yin Y (2015) Clustering of loop current patterns based on the satellite-observed sea surface height and self-organizing map. Remote Sens Lett 6(1):11–19
Acknowledgments
This work was supported by national funds through the Portuguese Foundation for Science and Technology (FCT), National Natural Science Foundation of China (Contact No. 11601129), and the European Regional Development Fund (FEDER) through COMPETE 2020—Operational Program for Competitiveness and Internationalization (POCI).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
AghaeiRad, A., Chen, N. & Ribeiro, B. Improve credit scoring using transfer of learned knowledge from self-organizing map. Neural Comput & Applic 28, 1329–1342 (2017). https://doi.org/10.1007/s00521-016-2567-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2567-2