Ensemble Learning Based Models and Deep Learning Model for Credit Prediction, Case Study: Taiwan, China

Mingyuan Han

2024

Abstract

As time progresses, credit prediction has become increasingly critical for banks and financial institutions. It serves to optimize fund allocation and mitigate the risk of non-performing loans, thereby contributing to the stability of the financial system. This study specifically delves into the credit market of Taiwan. Given the inherent incompleteness of the dataset, preprocessing methods are imperative to address data imbalances. Techniques such as oversampling, undersampling, and ensemble methods are employed for this purpose.Six machine learning models are utilized to train the system for credit prediction: Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Extreme Gradient Boosting (XGBoost), and Deep Neural Network (DNN). To assess the performance of these models, cross-validation and index evaluation methods are employed to ensure the robustness and reliability of the findings.Upon comparison of five performance metrics across the six models, XGBoost emerges as the most effective model for credit prediction in this context..

Paper Citation

in Harvard Style

Han M. (2024). Ensemble Learning Based Models and Deep Learning Model for Credit Prediction, Case Study: Taiwan, China. In Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI; ISBN 978-989-758-713-9, SciTePress, pages 115-121. DOI: 10.5220/0012910900004508

in Bibtex Style

@conference{emiti24,
author={Mingyuan Han},
title={Ensemble Learning Based Models and Deep Learning Model for Credit Prediction, Case Study: Taiwan, China},
booktitle={Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI},
year={2024},
pages={115-121},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012910900004508},
isbn={978-989-758-713-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI
TI - Ensemble Learning Based Models and Deep Learning Model for Credit Prediction, Case Study: Taiwan, China
SN - 978-989-758-713-9
AU - Han M.
PY - 2024
SP - 115
EP - 121
DO - 10.5220/0012910900004508
PB - SciTePress