Detection and Countermeasures for Security Fraud in Business Administration Based on Blockchain Technology in the Context of Big Data

Abstract

Fraud detection in business administration based on blockchain technology has emerged as a crucial direction in addressing the complexities of corporate transactions and data security requirements. This study integrates the decentralized and immutable characteristics of blockchain, introducing Random Forest and SMOTE algorithms to design a fusion model aimed at enhancing fraud detection performance and security. Experimental results demonstrate that this model significantly outperforms traditional models such as Random Forest, Support Vector Machine, and Logistic Regression in terms of accuracy (97.8%), precision (96.5%), recall (95.3%), and F1-score (95.9%). The combination of blockchain technology and improved algorithms can markedly improve the efficiency and security of fraud detection, providing a practical solution for complex fraud scenarios in the field of business administration.