Dynamic identification model of financial fraud of listed companies based on XGBoost and graph neural network

Key Points

• The research aims to develop a model for identifying financial fraud in listed companies using advanced algorithms.
• Utilized XGBoost algorithm for efficient prediction.
• Implemented graph neural network to analyze company relationships.
• Conducted data analysis on financial metrics of listed companies.
• The model significantly improved fraud detection rates compared to traditional methods.
• Demonstrated higher accuracy in identifying fraudulent transactions.
• Highlighted effective use of machine learning techniques in financial analysis.

Abstract