用多任务CNN建模交易行为序列，提升欺诈检测效率与准确率。
Multi-task CNN Behavioral Embedding Model For Transaction Fraud Detection
- 单层CNN搭配多尺度卷积核，兼顾性能与计算效率。
- 引入位置编码捕捉序列顺序，显著提升模型表现。
- 随机标签权重实现自动多任务学习，无需人工调参。
电商快速发展带来交易欺诈风险上升，深度学习在行为序列嵌入方面日益关键。然而现有方法常难以兼顾建模能力与效率，并缺乏领域知识融合。本文提出多任务CNN行为嵌入模型用于交易欺诈检测：1）采用单层CNN结合多尺度卷积核，相比LSTM与Transformer更具可扩展性与领域导向归纳偏置；2）将位置编码融入CNN以引入序列顺序信息，提升整体性能；3）通过随机分配标签权重实现多任务学习，避免人工调参。在真实数据上的测试表明，该模型显著提升了下游交易模型的性能，且与Transformer时间序列（TST）模型相当。
原文摘要 · Abstract (English)
The burgeoning e-Commerce sector requires advanced solutions for the detection of transaction fraud. With an increasing risk of financial information theft and account takeovers, deep learning methods have become integral to the embedding of behavior sequence data in fraud detection. However, these methods often struggle to balance modeling capabilities and efficiency and incorporate domain knowledge. To address these issues, we introduce the multitask CNN behavioral Embedding Model for Transaction Fraud Detection. Our contributions include 1) introducing a single-layer CNN design featuring multirange kernels which outperform LSTM and Transformer models in terms of scalability and domain-focused inductive bias, and 2) the integration of positional encoding with CNN to introduce sequence-order signals enhancing overall performance, and 3) implementing multitask learning with randomly assigned label weights, thus removing the need for manual tuning. Testing on real-world data reveals our model's enhanced performance of downstream transaction models and comparable competitiveness with the Transformer Time Series (TST) model.
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。