[论文解读] Advanced Payment Security System:XGBoost, LightGBM and SMOTE Integrated

Qi Zheng, Chang Yu+4 more|arXiv (Cornell University)|Jun 7, 2024

IPv6, Mobility, Handover, Networks, Security被引用 16

一句话总结

论文在支付风控中对XGBoost、LightGBM和CatBoost结合SMOTE进行评估，在关键指标上XGBoost+SMOTE为最佳表现。

ABSTRACT

With the rise of various online and mobile payment systems, transaction fraud has become a significant threat to financial security. This study explores the application of advanced machine learning models, specifically based on XGBoost and LightGBM, for developing a more accurate and robust Payment Security Protection Model. To enhance data reliability, we meticulously processed the data sources and applied SMOTE (Synthetic Minority Over-sampling Technique) to address class imbalance and improve data representation. By selecting highly correlated features, we aimed to strengthen the training process and boost model performance. We conducted thorough performance evaluations of our proposed models, comparing them against traditional methods including Random Forest, Neural Network, and Logistic Regression. Using metrics such as Precision, Recall, and F1 Score, we rigorously assessed their effectiveness. Our detailed analyses and comparisons reveal that the combination of SMOTE with XGBoost and LightGBM offers a highly efficient and powerful mechanism for payment security protection. Moreover, the integration of XGBoost and LightGBM in a Local Ensemble model further demonstrated outstanding performance. After incorporating SMOTE, the new combined model achieved a significant improvement of nearly 6\% over traditional models and around 5\% over its sub-models, showcasing remarkable results.

研究动机与目标

• 解决在线支付系统中的交易欺诈问题，采用先进的机器学习模型。
• 研究数据预处理步骤，包括异常值去除和特征相关性分析，以提升模型训练。
• 评估SMOTE对欺诈检测类别不平衡的影响。
• 在标准评估指标上，将梯度提升模型与传统分类器进行比较。

提出的方法

• 将LightGBM、XGBoost和CatBoost作为欺诈检测的主要模型。
• 应用SMOTE平衡不均衡的欺诈数据集，并在有/无SMOTE的条件下进行评估。
• 对选定特征(V14, V12, V10)进行数据清洗和异常值去除。
• 分析特征相关性并使用降维(t-SNE)进行可视化。
• 使用精确度、召回率、F1分数和ROC AUC对模型进行评估。
• 给出跨指标的模型性能对比表。

实验结果

研究问题

• RQ1 哪种梯度提升模型与SMOTE的组合可获得最佳欺诈检测性能？
• RQ2 数据预处理步骤（异常值去除、特征相关性分析）如何影响模型结果？
• RQ3 在支付欺诈检测中，先进模型是否优于传统分类器(KNN、SVM、逻辑回归等)？
• RQ4 XGBoost、LightGBM和CatBoost在精确度、召回率、F1和AUC上的相对优势？
• RQ5 SMOTE对所有模型是否有益，还是某些模型（如LightGBM）对重采样不太敏感？

主要发现

• XGBoost+SMOTE在综合指标上达到最高，精确度0.9999，召回率0.94，F10.969，AUC0.970。
• XGBoost在无SMOTE时已表现出色（Precision 0.9894, Recall 0.93, F1 0.958, AUC 0.9587）。
• CatBoost和LightGBM在若干指标上表现极强，CatBoost达到0.9999的精确度和0.958的召回率（F1 0.92；AUC 0.96）。
• LightGBM在无SMOTE时表现也异常出色，但SMOTE在若干模型中显著提升了精确度。
• 与传统模型(KNN、SVM、逻辑回归、决策树、神经网络)相比，梯度提升模型在欺诈检测上显示出显著的预测优势。
• 研究结论认为XGBoost+SMOTE是构建强健防欺诈支付系统的领先方法。