SQLBits 2024
First Class MLOps with Databricks
Deploying machine learning models still remains one of data science's largest challenge, but MLOps is your answer. We'll explore how Databricks can be an end-to-end MLOps tool and the one-stop solution to this problem. Session includes practical demos on: Mlflow, Feature Store, Real-Time Serving Endpoints and Model Monitoring.
Arguably the largest challenge in ML today is effectively deploying reliable and efficient models into production, with experts quoting that as many as 80% of model created never make it to production. MLOps streamlines the process of taking machine learning models to production, and then maintaining and monitoring them. With new MLOps micro-venders popping up every day, is there a tool that does everything?
In this session, we will consider Databricks as an end-to-end MLOps tool, exploring collaborative workspaces, feature stores, model registries and model serving, touching upon other critical MLOps practices such as model fairness, explainability and monitoring.
Including practical demos of Databricks Feature Store, MLFlow, Drift Monitoring and real-time Model Serving, this session is suitable for Data Scientists and Machine Learning Engineers of all levels.
In this session, we will consider Databricks as an end-to-end MLOps tool, exploring collaborative workspaces, feature stores, model registries and model serving, touching upon other critical MLOps practices such as model fairness, explainability and monitoring.
Including practical demos of Databricks Feature Store, MLFlow, Drift Monitoring and real-time Model Serving, this session is suitable for Data Scientists and Machine Learning Engineers of all levels.
