金融交易反欺诈人工智能建模方法研究  

Research on AI Modeling Approaches of Financial Transactional Fraud Detection

作　　者：钱亮宏 王福德 宋海龙 QIAN Lianghong;WANG Fude;SONG Hailong(Data Science Department,Yepdata Software Technology Company Limited,Shanghai 200233,China;Technology Department,Technical Department,Jilin Haicheng Technology Company Limited,Changchun 130119,China;Smart Agriculture Research Institute,Jilin Agricultural University,Changchun 130118,China)

机构地区：[1]益数软件科技(上海)有限公司数据科学部,上海200233 [2]吉林海诚科技有限公司技术部,长春130119 [3]吉林农业大学智慧农业研究院,长春130118

出　　处：《吉林大学学报（信息科学版）》2024年第5期930-936,共7页Journal of Jilin University（Information Science Edition）

基　　金：吉林省教育厅产业化培育基金资助项目(JJKH20240274CY)。

摘　　要：为解决金融交易反欺诈和维护金融安全,针对金融交易数据不平衡、类别离散的特点,提出一套端到端的建模流程、方法和模型结构。该流程涵盖数据预处理、模型训练和预测。同时比较了不同模型在不同特征数量情况下的效果和效率,并基于真实数据集进行验证,从而为金融机构根据自身的优化目标和资源限制选用不同类别和特征数量的模型提供参考。特征数较大(200以上)的基于树的模型适用于资源较充裕切追求极致模型效果的场景,中等规模(特征数100~200)的神经网络模型适用于资源一般的场景,而特征数较小的决策树模型或逻辑回归模型适用于资源有限且模型效果要求不高的长尾场景。Todetect transactional fraud in financial services industry and maintain financial security,an end-toend modeling framework,methodology,and model architecture are proposed for financial transactional data with imbalanced and discrete classes.The framework covers data preprocessing,model training,and model prediction.The performance and efficiency of different models with different numbers of features are compared and validated on a real-world dataset.The results demonstrate that the proposed approach can effectively improve the accuracy and efficiency of financial transactional fraud detection,providing a reference for financial institutions to select models with different types and numbers of features according to their own optimization goals and resource constraints.Tree-based models excel with over 200 features in resource-rich settings,while neural networks are optimal for medium-sized feature sets(100~200).Decision trees or logistic regression are suitable for small feature sets in resource-constrained,long-tail scenarios.

关 键 词：金融交易反欺诈 人工智能 模型选择 机器学习 深度学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]