系统梳理机器学习在数字银行反欺诈中的应用，揭示主流方法与未来趋势。
Machine learning for fraud detection in digital banking: a systematic literature review REVIEW
- 基于118篇文献的系统综述，按PRISMA标准筛选研究。
- 监督学习仍主导，深度模型在复杂欺诈检测中表现更优。
- 混合模型结合多种方法，适应性与准确率更高，适合实际部署。
本系统文献综述分析了机器学习在数字银行反欺诈中的作用，综合了118篇同行评审研究和机构报告。遵循PRISMA指南，通过结构化的识别、筛选、资格审查和纳入流程，确保方法严谨性和透明度。研究发现，决策树、逻辑回归和支持向量机等监督学习方法因可解释性和成熟性能仍是主流；而无监督异常检测方法正被越来越多用于处理高度不平衡数据集中的新型欺诈模式。深度学习架构，尤其是循环神经网络和卷积神经网络，已成为能够建模序列交易数据并检测复杂欺诈类型的变革性工具，但可解释性与实时部署挑战依然存在。结合监督、无监督和深度学习策略的混合模型展现出更高的适应性和检测准确率，凸显其作为集成解决方案的潜力。
原文摘要 · Abstract (English)
This systematic literature review examines the role of machine learning in fraud detection within digital banking, synthesizing evidence from 118 peer-reviewed studies and institutional reports. Following the PRISMA guidelines, the review applied a structured identification, screening, eligibility, and inclusion process to ensure methodological rigor and transparency. The findings reveal that supervised learning methods, such as decision trees, logistic regression, and support vector machines, remain the dominant paradigm due to their interpretability and established performance, while unsupervised anomaly detection approaches are increasingly adopted to address novel fraud patterns in highly imbalanced datasets. Deep learning architectures, particularly recurrent and convolutional neural networks, have emerged as transformative tools capable of modeling sequential transaction data and detecting complex fraud typologies, though challenges of interpretability and real-time deployment persist. Hybrid models that combine supervised, unsupervised, and deep learning strategies demonstrate superior adaptability and detection accuracy, highlighting their potential as convergent solutions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。