Add AI to your ETL: Cognitive Services + Apache Spark

Data enrichment can be a valuable step in ETL (extract, transform, load) pipelines. Enrichment often involves adding external attributes and pre-calculated values to improve analytics. This session describes why the AI capabilities of Cognitive Services are useful in taking data enrichment to the next level. It also covers how to use Cognitive Services in your Spark data pipelines through demos and example code. This session is geared toward data professionals with experience building Spark pipelines to load analytic data or for feature transformation. In this session you will learn: 1. Why AI services are helpful in data pipelines (ETL) 2. How Cognitive Services adds value to analytic datasets 3. How Databricks or Synapse Spark jobs can retrieve calculated values from Cognitive Services