Machine Learning in Astrato

Hemantkumar Member Posts: 4 Type 0.5

I am just try to figure out if we can do task for ML in Astrato,


  • joe_warbington
    joe_warbington Member, Partner, Customer Posts: 156 Type 2

    Hi @Hemantkumar - great question. We actually choose Snowflake as our main data platform because it works so well with a variety of needs in business intelligence, including ML and AI frameworks.

    "Snowflake was designed from the ground up to support machine learning and AI-driven data science applications. In conjunction with tight integrations to Spark, R, Qubole, and Python, Snowflake is an indispensable Data Science technology.

    Performance speed is a key factor in supporting robust machine learning models. Snowflake has the capabilities to scale up or scale down. It can also bear the data preparation responsibilities, reducing data-related burdens from machine learning tools.

    Snowflake offers some of the best cloud data analytics capabilities for data scientists and business analysts. "

    By working with those and other frameworks on the data, Astrato can consume that information directly and in near-real-time.

    Additionally, you'll see some forecasting abilities in the near future built directly into the Astrato charts and with upcoming Actions and Workflows, the ability to trigger an external task like "run a ML model" is being considered.

    What are you looking to do with Machine Learning?

  • Hemantkumar
    Hemantkumar Member Posts: 4 Type 0.5

    That is really great. Thanks for your informative content. Thanks @joe_warbington

  • MartinMahler
    MartinMahler Administrator, Moderator, Astrato PMs, Employee Posts: 11 admin

    @Hemantkumar picking this up again - is there a ML use case or example dataset within Snowflake that works well for this purpose? I'm trying to explore testing this myself on our dev version..

    Tel-Co churn predictions I think was a classic one? Any pointers would be highly appreciated! :)

  • Jochem
    Jochem Member, Partner Posts: 167 Type 2.5
    edited September 2022