A Novel Machine Learning-based Ensemble Model for Loan Prediction

DOI

10.2991/978-94-6463-823-3_25How to use a DOI?

Keywords

Machine Learning; Ensemble Model; Loan Prediction

Abstract

Loan prediction is important in business yield by enabling accurate credit risk assessment and improving decision-making. Incorrect credit evaluations can result in significant financial losses and impact both borrowers and lenders. To address the limitations of single machine learning models, such as poor generalization, overfitting and difficulty capturing complex feature interactions. This study develops a stacking ensemble framework to enhance prediction accuracy and robustness. The loan dataset is from Kaggle. There are some basic classifiers including K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), Naive Bayes, and Multilayer Perceptron (MLP) were trained and evaluated. The ensemble model combines the probabilistic outputs of top-performing models (KNN, RF, and GB) and uses K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB) as the meta model to optimize the final prediction. Techniques of data preprocessing such as Label Encoding and SMOTE were applied to handle categorical features and class imbalance. The result shows that the ensemble model is better than all individual models, achieving the highest accuracy of 88.51%. The ensemble model improved the performance of weaker models, such as GB, and maintained the predictive strength of RF. This study confirms that the ensemble model can improve the predictive performance and stability in loan risk assessment. Future research can explore deep learning-based meta models, adaptive ensemble strategies, and enhanced model interpretability for broader financial applications.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Cheuk Lam Lai
PY  - 2025
DA  - 2025/08/31
TI  - A Novel Machine Learning-based Ensemble Model for Loan Prediction
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 263
EP  - 273
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_25
DO  - 10.2991/978-94-6463-823-3_25
ID  - Lai2025
ER  -