Skip to content

machine-learning-on-bdc.md

Latest commit

 

History

History
44 lines (31 loc) · 2.78 KB

machine-learning-on-bdc.md

File metadata and controls

44 lines (31 loc) · 2.78 KB
Raw
title Machine Learning on SQL Server Big Data Clusters
titleSuffix SQL Server Big Data Clusters
description Machine Learning guide for SQL Server Big Data Clusters.
author HugoMSFT
ms.author hudequei
ms.reviewer wiassaf
ms.date 10/05/2021
ms.service sql
ms.subservice machine-learning-bdc
ms.topic conceptual

Machine Learning guide for SQL Server Big Data Clusters

[!INCLUDESQL Server 2019]

This article explains how to use [!INCLUDEbig-data-clusters-nover] for Machine Learning Scenarios.

[!INCLUDEbig-data-clusters-banner-retirement]

Introduction to Machine Learning in SQL Server Big Data Clusters

[!INCLUDEbig-data-clusters-nover] enables machine learning scenarios and solutions using different technology stacks: SQL Server Machine Learning Services and Apache Spark ML.

[!INCLUDEbig-data-clusters-nover] offer Machine Learning capabilities inside the SQL Server engine, using the established SQL Server Machine Learning Services technology stack; enabling a high-performance, in-database Machine Learning inference and scoring scenarios.

For big data-based machine learning scenarios, the usage of HDFS for big data hosting and Apache Spark ML capabilities is more cost-effective, scalable, and powerful.

Machine Learning Scenarios

The machine learning capabilities enable different applications and solutions such as: fraud detection, forecasting, churn, and general classification and regression tasks. Yet, it is important to use the best technology for a scenario.

Aspect SQL Server Machine Learning Services Apache Spark ML
Data placement Leverages tabular data locality on SQL Server. Premium data tier. Scalable Big Data data tier using HDFS; either unstructured, semi-structured, and structured data.
Best for Low latency inference and scoring scenarios 1. Distributed batch training and scoring machine learning models on top of Big Data
2. ETL sinks and large-scale data preparation and featurization for ML
Feeds ML powered BI dashboards, reports, and applications. Low latency required Batch scored data may be promoted to SQL Server to drive ML powered scenarios
Latency Low latency required Higher latency acceptable
Read more Run Python and R scripts with Machine Learning Services on SQL Server Big Data Clusters Introducing Spark Machine Learning on SQL Server Big Data Clusters

Next steps

For more information, see [Introducing [!INCLUDEbig-data-clusters-nover]](big-data-cluster-overview.md).