yellow and blue shapes yellow and blue shapes


Building Plaid's ML Fraud Detection Application, Signal


Renault Young

Renault Young
Software Engineer,
ML Infrastructure

Kevin Stumpf

Kevin Stumpf

Watch this virtual fireside chat to explore best practices in designing and deploying ML fraud detection applications. 

Our guest speaker, Renault Young, a Software Engineer at Plaid, joined Kevin Stumpf, CTO and Co-founder of Tecton, to do a deep dive into Renault's experiences in designing and developing Plaid’s ML infrastructure for Signal, Plaid's payment fraud detection and prevention application.

In this chat, Renault and Kevin discussed:

  • Overcoming the challenges faced during Plaid's quest for effective payment fraud detection, including how to solve for out-of-order transaction data
  • Technical solutions they adopted, including a new ML platform that allows for generating training datasets and designed for feature freshness and seamless large-scale production
  • The benefits derived from this new architecture—such as improved cost management, and better workspace and access controls—along with a look into future optimizations 

Watch On-Demand