Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 01012 | |
Number of page(s) | 14 | |
Section | Traffic Prediction and Analysis | |
DOI | https://doi.org/10.1051/itmconf/20257001012 | |
Published online | 23 January 2025 |
Research on Personal Loan Default Risk Assessment Based on Machine Learning
Aberdeen Institute of Data Science and Artificial Intelligence, South China Normal University, Foshan, China
Corresponding author: 20213801012@m.scnu.edu.cn
In the present era of rapid development of the Internet and big data, the scale of personal loans and the complexity of personal credit data are growing rapidly. Accurately assessing personal credit rating and personal loan default risk has become an important topic in the financial field. This paper analyzes the current research status of other scholars on machine learning in personal loan default risk assessment in recent years, and selects Logistic Regression, Support Vector Machine, Naïve Bayes and Deep Neural Networks as research model. Meanwhile, this paper selects the Kaggle website data of a bank and credit information bureau in India, preprocesses the dataset and applies it to the training and testing of the models, and finally derives the performance results of the four models. The results of the study show that the machine learning models have better accuracy and higher efficiency in analyzing personal credit data and assessing the risk of personal loan default. Among them, the Deep Neural Network has the best overall performance compared to the other three machine learning models. The research in this paper has certain research significance for the research of machine learning in personal loan default risk assessment.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.