This article applies the factorization machine (FM) model to credit risk assessment. One-hot encoding addresses non-numerical features, resulting in sparse data. The study compares FM's performance against logistic regression, support vector machine, k-nearest neighbors, and artificial neural network on four real-world datasets. Results show FM achieves higher accuracy and computational efficiency, making it a suitable candidate for credit risk assessment.
Publisher
Humanities and Social Sciences Communications
Published On
Feb 08, 2024
Authors
Jing Quan, Xuelian Sun
Tags
credit risk assessment
factorization machine
machine learning
data analysis
real-world datasets
Related Publications
Explore these studies to deepen your understanding of the subject.