Synergy Between Resilient Networks and Random Forests in Online Fraud Detection

Junxi Wang; Ningtao Sun; Yuhan Lv; Jiayi Zhou; Yue Xiao

doi:10.26689/jera.v9i2.9907

Junxi Wang School of Intelligent Manufacturing and Aviation, Zhuhai College of Science and Technology, Zhuhai 519041, Guangdong, China
Ningtao Sun School of Computer Science, Zhuhai College of Science and Technology, Zhuhai 519041, Guangdong, China
Yuhan Lv School of Liberal Arts, Zhuhai College of Science and Technology, Zhuhai 519041, Guangdong, China
Jiayi Zhou School of Logistics Management and Engineering, Zhuhai College of Science and Technology, Zhuhai 519041, Guangdong, China
Yue Xiao School of Data Science, Zhuhai College of Science and Technology, Zhuhai 519041, Guangdong, China

DOI: https://doi.org/10.26689/jera.v9i2.9907

Keywords: Fraudulent websites, Machine learning, Elastic Net, Random Forests

Abstract

This paper explores the synergistic effect of a model combining Elastic Net and Random Forest in online fraud detection. The study selects a public network dataset containing 1781 data records, divides the dataset by 70% for training and 30% for validation, and analyses the correlation between features using a correlation matrix. The experimental results show that the Elastic Net feature selection method generally outperforms PCA in all models, especially when combined with the Random Forest and XGBoost models, and the ElasticNet + Random Forest model achieves the highest accuracy of 0.968 and AUC value of 0.983, while the Kappa and MCC also reached 0.839 and 0.844 respectively, showing extremely high consistency and correlation. This indicates that combining Elastic Net feature selection and Random Forest model has significant performance advantages in online fraud detection.