Machine Learning Model and Financial Feature Fusion for Innovative Enterprise Credit Assessment in Digital Supply Chain Finance
Journal of Economic Theory and Business Management · 2025
DOI: 10.70393/6a6574626d.333539 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Economic Theory and Business Management, 2025. Verfasst von Ningai Leng und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
With the digital transformation of supply chain finance, traditional credit assessment methods have become increasingly inadequate in addressing the information asymmetry and risk transmission issues faced by innovative enterprises. This study proposes a hybrid machine learning framework integrating XGBoost feature selection and LSTM (Long Short-Term Memory) prediction to enhance the accuracy and interpretability of credit assessment. By constructing a multi-dimensional feature system that combines 18 financial indicators and 6 digital supply chain features, the model realizes dynamic risk identification for innovative enterprises. Based on a sample of 1,357 observations from 85 Chinese-listed innovative enterprises between 2019 and 2023, empirical results show that the proposed XGBoost-LSTM model achieves an accuracy of 98.2%, a recall rate of 97.5%, and an F1-score of 97.8%, outperforming traditional Logistic regression (82.3%), single XGBoost (94.1%), and MLP (Multi-Layer Perceptron) (95.6%) models. The research confirms that the fusion of operating cash flow stability, accounts receivable turnover efficiency, and supply chain transaction integrity significantly improves credit assessment performance. This study provides a feasible technical solution for financial institutions to implement precise risk control in digital supply chain finance.
Zitieren
APA
Leng, N., Zhou, J., Ma, H., & Shi, J. (2025). Machine Learning Model and Financial Feature Fusion for Innovative Enterprise Credit Assessment in Digital Supply Chain Finance. Journal of Economic Theory and Business Management. https://doi.org/10.70393/6a6574626d.333539
Vancouver
Leng N, Zhou J, Ma H, Shi J. Machine Learning Model and Financial Feature Fusion for Innovative Enterprise Credit Assessment in Digital Supply Chain Finance. Journal of Economic Theory and Business Management. 2025. doi:10.70393/6a6574626d.333539
BibTeX
@article{Leng2025,
author = {Leng, Ningai and Zhou, Jinghan and Ma, Huichen and Shi, Jianbu},
title = {Machine Learning Model and Financial Feature Fusion for Innovative Enterprise Credit Assessment in Digital Supply Chain Finance},
journal = {Journal of Economic Theory and Business Management},
year = {2025},
doi = {10.70393/6a6574626d.333539}
}
EUVIMED