Applying Graph Algorithms and Graph Convolutional Networks for Advertising Anti‑Fraud at 58.com

This article explains how various graph algorithms—including connected components, label propagation, Louvain community detection, and Graph Convolutional Networks—are built on large‑scale user‑behavior graphs using Spark GraphX to detect and mitigate advertising fraud, detailing methodology, implementation, and experimental results.

GCNSpark GraphXanti-fraud

0 likes · 13 min read

Applying Graph Algorithms and Graph Convolutional Networks for Advertising Anti‑Fraud at 58.com

58 Tech

Nov 18, 2020 · Artificial Intelligence

Applying Graph Algorithms and Graph Convolutional Networks to Advertising Anti‑Fraud

This article describes how graph theory and graph convolutional neural networks are leveraged to model user‑IP relationships, detect fraudulent advertising clusters, and improve detection accuracy and recall through a combination of unsupervised graph algorithms and supervised GCN training in a large‑scale ad‑anti‑fraud system.

AdvertisingGCNSpark GraphX

0 likes · 14 min read

Applying Graph Algorithms and Graph Convolutional Networks to Advertising Anti‑Fraud

ITPUB

Nov 18, 2020 · Databases

How JanusGraph and Spark GraphX Unlock Value Users in 58 Tribe’s Social Network

This article details how 58 Tribe built a large‑scale graph database with JanusGraph, integrated it with Spark GraphX to compute degree, closeness and betweenness centralities, optimized batch imports, identified cheating and high‑value users, and achieved significant performance gains for social network analysis.

JanusGraphSocial Network AnalysisSpark GraphX

0 likes · 16 min read

How JanusGraph and Spark GraphX Unlock Value Users in 58 Tribe’s Social Network

58 Tech

Oct 16, 2020 · Big Data

Social Network Analysis and Graph Database Solution for 58 Community Using JanusGraph and Spark GraphX

This article describes how the 58 community builds a large‑scale social network graph, evaluates graph databases such as Neo4j, JanusGraph and HugeGraph, implements centrality metrics with Spark GraphX, and designs a JanusGraph‑based pipeline for detecting valuable and fraudulent users.

JanusGraphSocial Network AnalysisSpark GraphX

0 likes · 16 min read