Back to Events
On Demand

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.

‍

Join upcoming demo

Register with SlackSlack
‍

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.

‍

Learn more from top AI experts

Qwak webinar logo

MLOps best practices for Generative AI

MLOps best practices for Generative AI
On Demand
MLOps best practices for Generative AIMLOps best practices for Generative AIMLOps best practices for Generative AI
Guy Eshet
,
,
,
Qwak webinar logo

Building an Optimized ML Pipeline

The builders behind Superbet’s profanity detection model
On Demand
Building an Optimized ML PipelineBuilding an Optimized ML PipelineBuilding an Optimized ML PipelineMateja Iveta
Pavel Klushin
,
Filip Gvardijan
,
Zvonimir Cikojevic'
,
Mateja Iveta
Qwak webinar logo

Building the World's First AI-Powered Sports Narrator

The only one of its kind
On Demand
Building the World's First AI-Powered Sports NarratorBuilding the World's First AI-Powered Sports NarratorBuilding the World's First AI-Powered Sports Narrator
Chen Margalit
,
,
,

JFrog ML helps companies deploy AI in production

“JFrog ML 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 JFrog ML. I wish we had found them sooner.”
Upside
“The JFrog ML platform enabled us to deploy a complex recommendations solution within a remarkably short timeframe. JFrog ML is an exceptionally responsive partner, continually refining their solution.”
Lightricks
See how our customers win with JFrog ML
right arrow