Back To Schedule
Tuesday, October 8 • 5:00pm - 5:50pm
PRO WORKSHOP (AI): Graph Deep Learning for Entity Scoring in eCommerce Fraud Prediction

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Recent years, inspired by the huge success of convolutional networks in Computer Vision, Graph Convolutional Networks has emerged and attracted great attention for its potentials in graph-based data world, such as social networks, recommendation, biological graphs and traffic prediction. In this talk, we present our innovation on fraud prediction of using Graph Convolutional Networks (GCNs) in Walmart eCommerce system where it predicts risk scores for entities (e.g. customer, device) in real time on large-scale transaction-based graphs. We demystify how it smartly leverages graph topology via adjacency matrix and learn the weight matrices to nonlinearly propagate information across multi-hop graphs, especially on graphs condensed of fraudulent transactions. We also describe how the semi-supervised classification GCNs is trained with a weighted softmax loss function on partially labeled graph snapshots. By comparing with models that do not rely on graph structures, we show the noticeable performance lift of GCNs in various aspects. To demonstrate how well it works, we evaluate the prediction results through real-world graph examples at WalmartLabs. At the end, we show the significant business/engineering value our entity scores can bring to the company and point out multiple directions in which the methodologies can be generalized and further improved.

AI DevWorld 2019 Speakers
avatar for Xu Si

Xu Si

Sr. Data Scientist at WalmartLabs, WalmartLabs
Xu Si is a Senior Data Scientist at WalmartLabs, where she works on the end-to-end project in fraud prediction for Walmart transactions that prevents millions of revenue loss due to fraud every year. Her current research area is in applying graph deep learning on entity scoring and... Read More →
avatar for Yiyi Zeng

Yiyi Zeng

Principal Data Scientist, WalmartLabs
Yiyi Zeng is a senior manager/principal data scientist at Wal-Mart Labs. Yiyi has 12 years of extensive experience in business analytics and intelligence, decision management, fraud detection, credit risk, online payment and e-commerce across various business domains including both... Read More →

Tuesday October 8, 2019 5:00pm - 5:50pm PDT
AI DevWorld -- Workshop Stage 1