arXiv:1903.05976
Empirical effect of graph embeddings on fraud detection/ risk mitigation
원문 초록
Graph embedding technics are studied with interest on public datasets, such as BlogCatalog, with the common practice of maximizing scoring on graph reconstruction, link prediction metrics etc. However, in the financial sector the important metrics are often more business related, for example fraud detection rates. With our privileged position of having large amount of real-world non-public P2P-lending social data, we aim to study empirically whether recent advances in graph embedding technics provide a useful signal for metrics more closely related to business interests, such as fraud detection rate.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Efficient Identity and Position Graph Embedding via Spectral-Based Random Feature Aggregation
Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition
Optimal Embedding Guided Negative Sample Generation for Knowledge Graph Link Prediction
Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding for Traffic Forecasting
On Large-scale Evaluation of Embedding Models for Knowledge Graph Completion
Open-World Social Event Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.