Often building Machine Learning (ML) pipelines can be complicated due to the tools and in-depth technical knowledge required to make and deploy the right forecast models.
AutoML systems provide a black-box solution to these problems looking for the right way to process and select features, choosing an algorithm and performing hyperparameters fine-tuning of the entire pipeline.
It is possible in the end, for a wide range of users, to exploit all the power of predictive analysis even without a deep machine learning experience by recalling these AutoML systems even from non-canonical model development environments, such as a DWH query shell.
What we will talk about
In this webinar we will talk about how it becomes increasingly important and strategic to reduce the gap between the experimentation environment and the use of a chosen analysis model in a business process that involves advanced data analysis.
The integration of AWS SageMaker Autopilot functions in Snowflake allows you to reduce this gap, bringing close to the organized data an analysis environment suitable for experimenting, creating and then making accessible models designed for a given business case.
Then we will see together in a demo this winning integration between AWS and Snowflake at work.
- Serving ML models
- AWS SageMaker Autopilot
- Snowflake External Function
This webinar is designed for CIOs, Data Architects, Data Engineers and business users of medium and large companies.
For any information contact us at email@example.com
Sign up to Quantyca's Newsletter to stay updated on our events, webinars and other initiatives! Link per l'iscrizione