Research on Supply Chain Financial Risk Prevention Based on Machine Learning.

Area of Science:

• Supply Chain Management
• Financial Technology
• Artificial Intelligence

Background:

• Globalization uncertainties and events like COVID-19 increase bankruptcy risks for supply chain enterprises.
• Existing systems lack timely threat identification and response mechanisms for financial crises.
• Transformation to intelligent supply chains is crucial for enhanced management and operational efficiency.

Purpose of the Study:

• To develop an artificial intelligence-based corporate financial risk prevention (FRP) model for supply chains.
• To enhance decision-making capabilities for mitigating financial risks and preventing business failure.
• To promote the transformation of traditional supply chains into intelligent, resilient systems.

Main Methods:

• Data preprocessing and feature selection using the chaotic grasshopper optimization algorithm (CGOA).
• Classification of financial data using support vector machine (SVM) with hinge loss function.
• Optimization of SVM efficiency and accuracy using the slime mould algorithm (SMA).

Main Results:

• The proposed CGOA-SVM-SMA algorithm demonstrated superior prediction and decision-making capabilities compared to other models.
• The AI-based FRP model effectively identifies potential risks and guides preventative measures.
• The study successfully simulated the corporate business finance risk prevention model using Python.

Conclusions:

• The CGOA-SVM-SMA algorithm provides an effective tool for supply chain financial risk prevention.
• AI-driven decision-making enhances the ability of enterprises to navigate financial uncertainties.
• The developed model supports the transition to smarter, more robust supply chain operations.