The Life of a Feature - a Journey Through Space and Time

Enhancing ML accuracy by aligning time and features to avoid label leakage
Ron Tal
Ron Tal
ML and Data Infra Engineer at CloudTrucks
at
at
at

One of the most common mistakes when training and deploying a machine learning model is making sure that the feature values align properly with time. This leads to things such as label leakage, where the value of the feature changed based on the eventual outcome. In this talk, Ron will be taking the audience on a journey through space and time, drawing on his experience from Uber, Coinbase and CloudTrucks, to demonstrate how rethinking features as a result of discrete events, and a proper data infrastructure can lead to better models and more consistent real-time performance.

‍

‍

One of the most common mistakes when training and deploying a machine learning model is making sure that the feature values align properly with time. This leads to things such as label leakage, where the value of the feature changed based on the eventual outcome. In this talk, Ron will be taking the audience on a journey through space and time, drawing on his experience from Uber, Coinbase and CloudTrucks, to demonstrate how rethinking features as a result of discrete events, and a proper data infrastructure can lead to better models and more consistent real-time performance.

‍

Qwak optimizes AI in production

“Qwak streamlines AI development from prototype to production, freeing us from infrastructure concerns and maximizing our focus on business value.”
Notion
“We ditched our in-house platform for Qwak. I wish we had found them sooner.”
Upside
“The Qwak platform enabled us to deploy a complex recommendations solution within a remarkably short timeframe. Qwak is an exceptionally responsive partner, continually refining their solution.”
Lightricks