The Advancements of Machine Learning Algorithms in Lending Systems for Predicting Lending Behavior

Ruoxuan Zhao

2024

Abstract

Machine learning is indispensable for people to predict the data to make decisions wisely. Especially in the lending system, predicting the lending behavior of customers will affect the decision making of lending platforms or individuals, which in turn will affect the development of the whole economy, so it is worthwhile to pay attention to the application of machine learning to train models to predict the lending behavior. Machine learning workflows typically include data collection and cleaning, model selection and training, evaluation, parameter tuning, and final prediction. Deep learning further enhances this process by using artificial neural networks that employ a hierarchical structure. This paper works on traditional ML-based prediction methods, including decision trees and logistic regression, and compares them to deep learning-based methods such as Long Short-Term Memory (LSTM) networks and Back Propagation (BP) neural networks. Decision trees effectively classify loan applicants by evaluating attributes, while logistic regression models are relatively easy and fast to train. LSTM networks with enhanced attentional mechanisms handle long-term data flexibly, while BP neural networks excel in complex data processing. This comparative study highlights the advantages and applications of various machine learning and deep learning techniques in predictive modeling.

Paper Citation

in Harvard Style

Zhao R. (2024). The Advancements of Machine Learning Algorithms in Lending Systems for Predicting Lending Behavior. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 387-392. DOI: 10.5220/0013263800004568

in Bibtex Style

@conference{ecai24,
author={Ruoxuan Zhao},
title={The Advancements of Machine Learning Algorithms in Lending Systems for Predicting Lending Behavior},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={387-392},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013263800004568},
isbn={978-989-758-726-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - The Advancements of Machine Learning Algorithms in Lending Systems for Predicting Lending Behavior
SN - 978-989-758-726-9
AU - Zhao R.
PY - 2024
SP - 387
EP - 392
DO - 10.5220/0013263800004568
PB - SciTePress