Predicting Credit Worthiness of Bank Customer with Machine Learning over Cloud
Year: 2018
Type: article
Abstract: 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
Authors: A. Motwani, P. Chaurasiya, G. Bajaj
Language: English
Subfield: Accounting
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W2885074009