How PayPal Uses Large Graph Neural Networks to Detect Bad Actors | Experiment Exchange
How do you detect fraud when less than one percent of your network’s users are bad actors?
In this episode, SigOpt’s Head of Engineering Michael McCourt speaks with Venkatesh Ramanathan, a Director of Data Science at PayPal, about his work using Graph Neural Networks to detect fraud across large financial networks.
0:23 - Intro
3:08 - AI/ML at AOL
4:24 - The scale of data today
6:11 – The tradeoffs of accuracy and interpretability
7:54 - What are Graph Neural Networks?
9:18 - Robustness of GNNs; how they work with blockchain networks
10:57 - The need for robust hardware for GNNs
12:44 - How PayPal uses SigOpt for hyperparameter search
15:12 - The importance of sample efficiency
16:51 - What's next for Data Science at PayPal
20:52 - Opportunities for academia to power industry insights
Subscribe to Experiment Exchange on your favorite podcast platform, available now on Spotify, Apple Podcasts, and more!
✔️ Learn more about SigOpt: https://sigopt.com
✔️ Follow us on Twitter at / sigopt
![[FREE] Digga D x Hazey x M1llionz x Unknown T Type Beat -](https://images.videosashka.com/watch/qfnoLByhXRw)
