How to automate machine learning on SQL Server 2019 big data clusters

In this post, we will explore how to use automated machine learning (AutoML) to create new machine learning models over your data in SQL Server 2019 big data clusters. SQL Server 2019 big data clusters make it possible to use the software of your choice to fit machine learning models on big data and use those models to perform scoring. In fact, Apache SparkTM, the popular open source big data framework, is now built in! Apache SparkTM includes the MLlib Machine Learning Library, and the open source community has developed a wealth of additional packages that integrate with and extend Apache SparkTM and MLlib. Manually selecting and tuning machine learning models requires familiarity with a variety of model types and can be laborious and time-consuming.