#7 How DoorDash maintains models accuracy through a monitoring system.
www.machinelearningatscale.com
Introduction The main topic of this article is: "How can we fight model drift?" As soon as a model is trained, validated and deployed to production, it begins degrading. Inputs and outputs need to be closely monitored to diagnose and better yet prevent model drift.
#7 How DoorDash maintains models accuracy through a monitoring system.
#7 How DoorDash maintains models accuracy…
#7 How DoorDash maintains models accuracy through a monitoring system.
Introduction The main topic of this article is: "How can we fight model drift?" As soon as a model is trained, validated and deployed to production, it begins degrading. Inputs and outputs need to be closely monitored to diagnose and better yet prevent model drift.