Predictive Analysis of Credit Score for Credit Card Defaulters
Nupura Torvekar1, Pravin S. Game2
Manuscript received on 06 February 2019 | Revised Manuscript received on 19 February 2019 | Manuscript Published on 04 March 2019 | PP: 283-286 | Volume-7 Issue-5S2 January 2019 | Retrieval Number: ES2048017519/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Risk management has always been an important aspect of the financial institutions. Apart from the consumer frauds that cause huge losses, one more source of credit risk is nothing but the loan defaulters. Appropriate loan granting decisions therefore play an important role in avoiding these losses. Credit score and credit scoring which depends upon the credit history of a customer is one among the many factors that contribute to the loan granting decisions. Prediction of the loan defaulters in advance can help the financial institutions in undertaking some preventive measures to avoid granting loans to customers with potential risk and thereby reducing the amount of bad loans. Various machine learning techniques can play an important role in the identification of loan defaulters. The proposed work aims to identify and distinguish the good customers from bad customers by using different machine learning techniques. Two different tools Waikato Environment for Knowledge Analysis (WEKA) and KNIME (Konstanz Information Miner) are used for analyzing the performance of the classifiers. The main focus of this work is the prediction of credit card defaulters and hence two data sets relating to the credit card data of customers have been used for the purpose of this study. The results obtained from the proposed work can help the financial institutions in the identification and control of credit risk.
Keywords: Classification; Machine Learning Techniques; Risk Management.
Scope of the Article: Predictive Analysis