GNNs for Fraud Detection from Industry Leaders

Leaders from various industries will speak on how graph neural networks have been used in fraud detection use cases to unlock critical business benefits. Financial fraud, fake reviews, bot assaults, account takeovers, and spam are all examples of online fraud and harmful activity. In recent years, GNNs have gained traction for fraud detection problems, revealing suspicious nodes (in accounts and transactions, for example) by aggregating their neighborhood information through different relations — in other words, by checking whether a given account has sent a transaction to a suspicious account in the past. In the context of fraud detection, the ability of GNNs to aggregate information contained within the local neighborhood of a transaction enables them to identify larger patterns that may be missed by just looking at a single transaction. Hear from industry leaders like Mastercard, TigerGraph, Bunq, and BNY Mellon.