Fraud Detection with Graph Features and Graph Neural Networks

Jan 31, 12:00PM PDT(08:00PM GMT).
  • Virtual SF Big Analytics
  • Free 103 Attendees

Why do we need Graph Features and Graph Neural Networks for Fraud Detection? See some reasons below:
- Class Imbalance, Label Scarcity & Fidelity (Fraud cases are rare events)
- Fraud Camouflage - handle context & feature inconsistency (i.e. fraudsters connecting to regular entities)
- Investigation and Exploration (visual way to connect the dots)
- Anomaly Detection - handle point, structural and contextual outliers
- Graph Embeddings - combined with NLP, could be used for scalable fuzzy search and entity resolution
- Explainability & fairness - adding the context and structure for interpretation, rebalancing the data to remove bias.
That is why Facebook, Amazon, Tencent, Alibaba and eBay are using Graph for Fraud Detection.

Nikita Iserson

Nikita Iserson is a Lead Machine Learning Engineer at S&P Global with over 10 years of experience in software engineering, data engineering and machine learning. He has built fraud detection, demand forecasting, network analysis, recommender systems, digital twins, and much more covering a wide range of industries, including telecom, retail, and banking, mainly using open-source technologies like Python, PyTorch and Spark.
The event ended.
Watch Recording
*Recordings hosted on Youtube, click the link will open the Youtube page.
Contact Organizer