Machine Learning Techniques in Credit Default Prediction

Digital transformation after the pandemic is a must if a company wants to survive in a highly competitive environment. Machine Learning (ML) applications are no strangers to Digital Transformations, and banks are looking for ways to improve efficiency by means of similar technologies. In this work, we propose a machine learning model for predicting the credit default using the LendingClub public dataset. The accepted loans include data ranging from 2007 to 2017. For this purpose, we implement support vector machines and logistic regression models. The results showed that support vector machines is a high accurate model (93%) for predicting the credit default. © 2023 Springer Nature Switzerland AG. Part of Springer Nature.