Using Machine Learning (ML) and data analytics in the banking organizations is more than a trend and has become essential to keep up with the market competition and reduce credit risks. In recent years, Customer’s Credit Worthiness is becoming more crucial for financial organizations. In past many credit risk models, that are actually statistical tools, are used to infer the future probabilities of customers to become default. At the same time with the massive increase in the volume, variety and velocity of data generated through various banking and business transactions pose a great computational and storage challenge for data analysis and intelligence tasks. To address the challenges for intelligence tasks Cloud Computing (CC) paradigm is evolved. The data and computation can be distributed to any CC environment with minimal effort nowadays. Also, CC paradigm turned out to be valuable alternatives to speed-up ML platforms. This paper aims to build and assess the performance of the 03 machine learning models, for prediction of credit card payment defaulter, over Microsoft Azure Machine Learning Platform. Finally a predictive analytics framework for classifying and predicting payment default by credit holder is proposed. For developing and testing the model a large, real and recent dataset of credit card, obtained from UCI repository, is used. The key focus of the work is on detection of Credit Worthiness which is defined as the ‘probability of default’ on the loan or credit from financial organizations like banks. The efficacy of model is demonstrated, on the basis of prediction accuracy and other metrics, against benchmark classifiers. Proposed work also demonstrates the use of Microsoft Azure cloud which is one of the foremost cloud environments for ML. The results attained by the proposed model are promising and the obtained results have potential to direct the future research work in domain.

Artificial Intelligence, Predictive Modelling, Cognitive Computing, Computer Vision, Credit Risk, Credit Worthiness, Data Classification, Financial Organization, Machine Learning, Microsoft Azure, Cloud Computing

[1] https://www.investopedia.com/terms/c/credit-worthiness.asp
[2] https://www.moodys.com/sites/products/ProductAttachments/CreditMonitor_brochure.pdf
[3] Usama Fayyad, Gregory Piatetsky-Shapiro, and Padhraic Smyth, “From Data Mining to Knowledge Discovery in Databases”,American Association for Artificial Intelligence. All rights reserved. 0738-4602-1996.
[4] Sebastiaan Tesink,” Improving Intrusion Detection Systems through Machine Learning” Tilburg University March 2007.
[5] K. Tumer and N. C. Oza, “Decimated input ensembles for improved generalization,” in Proceedings of the International Joint Conference on Neural Networks (IJCNN `99), pp. 3069–3074, Washington, DC, USA, July 1999.
[6] Belady C. “In the data center, power and cooling costs more than the it equipment it supports” 2007. URL: http://www.electronics-cooling.com/articles/2007/feb/a3/.
[7] National Institute of Standards and Technology (2011) NIST cloud computing reference architecture: Version 1. NIST Meeting Report
[8] P. Mell, T. Grance, “The NIST Definition of Cloud Computing, National Institute of Standards and Technology”, ver. 15, 9 July 2010.
[9] Regina Esi Turkson, Edward Yeallakuor Baagyere, Gideon Evans Wenya, “A Machine Learning Approach for Predicting Bank Credit Worthiness”, ISBN: 978-1-4673-9187-0, IEEE 2016
[10] Ling Kock Sheng, and Teh Ying Wah, “A comparative study of data mining techniques in predicting consumers’ credit card risk in banks”, African Journal of Business Management Vol. 5 (20), pp. 8307-8312, 16 September, 2011
[11] Loris Nanni , Alessandra Lumini, “An experimental comparison of ensemble of classifiers for bankruptcy prediction and credit scoring”, Elsevier, Expert Systems with Applications 36 (2009) 3028–3033.
[12] U Bhuvaneswari, P. James Daniel Paul, Siddhant Sahu, “Financial Risk Modelling in Vehicle Credit Portfolio”, 978-1-4799-4674-7/14/$31.00, IEEE 2014
[13] C.R.Durga devi, Dr.R.Manicka chezian, “A Relative Evaluation of the Performance of Ensemble Learning in Credit Scoring”, IEEE International Conference on Advances in Computer Applications (ICACA), 978-1-5090-3770-4/16, 2016
[14] David Opitz and Richard Maclin, “Popular Ensemble Methods: An Empirical Study”, Journal of artificial intelligence research 169-198, 1999.
[15] L. Breiman, “Bagging predictors,” Machine Learning, vol. 24, no. 2, pp. 123–140, 1996.
[16] Freund, Y., & Schapire, R. (1996), “Experiments with a new boosting algorithm”, in Proceedings of the thirteenth international conference on machine learning, Bari, Italy, pp. 148–156.
[17] Wolpert, D. H. (1992). Stacked generalization, Neural Networks, 5(2), 241–259.
[18] Gang Wang, Jinxing Hao, Jian Mab, Hongbing Jiang, “A comparative assessment of ensemble learning for credit scoring”, Expert Systems with Applications 38 (2011) 223–230.
[19] K. Tumer and N. C. Oza, “Decimated input ensembles for improved generalization,” in Proceedings of the International Joint Conference on Neural Networks (IJCNN `99), pp. 3069–3074, Washington, DC, USA, July 1999.
[20] Anand Motwani, Goldi Bajaj, Sushila Mohane, "Predictive Modelling for Credit Risk Detection using Ensemble Method", International Journal of Computer Sciences and Engineering, Vol.6, Issue.6, pp.863-867, 2018.
[21] Sihem Khemakhem ,and Younés Boujelbènea, “Credit risk prediction: A comparative study between discriminant analysis and the neural network approach”, Accounting and Management Information Systems Vol. 14, No. 1, pp. 60-78, 2015
[22] https://aws.amazon.com/aml/
[23] https://cloud.google.com/products/machine-learning/
[24] https://cloud.google.com/ml-engine/
[25] https://azure.microsoft.com/en-in/services/machine-learning-studio/
[26] Weka, University of Waikato, Hamilton, New Zealand., http://www.cs.waikato.ac.nz/~ml/weka/index.html
[27] http://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients