Downloads: 0 | Views: 94

Research Proposals or Synopsis | Computer Engineering | India | Volume 12 Issue 6, June 2023

Default of Credit Card Clients Prediction Using ML Algorithms

Rupali Dasarwar | Deepali C. Gajbhiye

Abstract: This study aims to use a decision tree machine learning model to predict credit card defaults using imbalanced datasets. Imbalanced datasets occur when the number of observations in one class is significantly lower than the number of observations in the other class. In the context of credit card defaults, this means that the number of non - defaulting cases is much higher than the number of defaulting cases. This poses a challenge for machine learning models, as they may be biased towards the majority class. The data used for this analysis includes demographic information and credit card usage patterns of individuals. The decision tree algorithm will be used to train and test the model using this data. The study will first perform an exploratory data analysis, then data will be pre - processed and cleaned before modeling. The model will be trained and tested using different techniques to handle imbalanced data, such as oversampling and under sampling, and the results will be evaluated using metrics such as accuracy, precision, and recall. The goal of this study is to provide insight into the factors that contribute to credit card defaults and to develop a model that can assist in identifying individuals at risk of default, even when the data is imbalanced. By identifying these individuals, lenders can take steps to mitigate the risk of default, such as offering credit counseling or adjusting credit limits. Additionally, the findings of this study could also be used to inform public policy decisions related to consumer credit. In conclusion, this study aims to use a decision tree machine learning model to predict credit card defaults using imbalanced datasets. The results of this study could be used to assist in identifying individuals at risk of default, which would be of great value to lenders and could help to mitigate the risk of credit card defaults. The study will explore the different techniques to handle imbalanced data to improve the model performance.

Keywords: Accuracy, precision, recall, metrics, Credit card defaults, Imbalanced datasets, Exploratory data analysis, Risk identification

Edition: Volume 12 Issue 6, June 2023,

Pages: 1775 - 1778