Graph Neural Networks in Real-Time Fraud Detection with Lambda Architecture

10/09/2021
by   Mingxuan Lu, et al.
Shanghai Jiao Tong University
0

Transaction checkout fraud detection is an essential risk control components for E-commerce marketplaces. In order to leverage graph networks to decrease fraud rate efficiently and guarantee the information flow passed through neighbors only from the past of the checkouts, we first present a novel Directed Dynamic Snapshot (DDS) linkage design for graph construction and a Lambda Neural Networks (LNN) architecture for effective inference with Graph Neural Networks embeddings. Experiments show that our LNN on DDS graph, outperforms baseline models significantly and is computational efficient for real-time fraud detection.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/25/2022

BRIGHT – Graph Neural Networks in Real-Time Fraud Detection

Detecting fraudulent transactions is an essential component to control r...
10/13/2022

Behavioral graph fraud detection in E-commerce

In e-commerce industry, graph neural network methods are the new trends ...
12/20/2020

Suspicious Massive Registration Detection via Dynamic Heterogeneous Graph Neural Networks

Massive account registration has raised concerns on risk management in e...
07/25/2019

Graph Neural Lasso for Dynamic Network Regression

In this paper, we will study the dynamic network regression problem, whi...
12/13/2018

Conditional Graph Neural Processes: A Functional Autoencoder Approach

We introduce a novel encoder-decoder architecture to embed functional pr...

Please sign up or login with your details

Forgot password? Click here to reset