In this talk, we will take the next step after training machine learning models: Building a prediction service that uses a machine learning model using only Python and free serverless services. We will show the importance of a feature store for managing features for both training and serving in prediction services. We will show how Hopsworks 3.0, both the first Python centric and first serverless feature store, brings features stores to the masses with an easy to use API and no infrastructure to manage.
The Feature Store is the essential part of AI infrastructure that helps organisations bring modern enterprise data to analytical and operational ML systems. It is the simplest most powerful way to get your models to production. From anywhere, to anywhere.From months, to minutes.