0 views collected around this technical thread.
This article explores how black‑market cheating in marketing campaigns and e‑commerce is detected using graph‑based techniques such as same‑person mining, label propagation, Fraudar, and GCN models, and discusses future directions like multimodal data fusion and real‑time dynamic graph computation.
This article presents graph‑based fraud detection techniques for advertising traffic, detailing dense subgraph algorithms such as Fraudar and D‑Cube, their engineering optimizations, real‑world case studies, and the design of a scalable graph‑mining platform for large‑scale security applications.
The article presents a comprehensive overview of e‑commerce fraud, especially brush‑order schemes, and introduces the Fraudar algorithm—a graph‑based unsupervised method that leverages bipartite network analysis, global suspiciousness metrics, priority‑tree optimization, and collaborative supervised training to efficiently identify dense fraudulent sub‑graphs.