Salesforce Docs Portal

Use Databricks Models

You can build, train, and deploy custom machine learning models with Databricks and data in Salesforce. After registering a model in Databricks, define your prediction criteria and connect the model with Data 360 to get predictions and insights for your use case. Use the insights to enrich customer profiles, create segments, and personalize experiences across various channels.

Required Editions

Available in: Developer, Enterprise, Performance, and Unlimited editions

Here are some benefits of using a Databricks model with Salesforce data.

  • Access highly curated, harmonized, and near real-time data across Customer 360. This capability leads to expert models that deliver more intelligent predictions.
  • Build models in Databricks and easily connect them with Data 360 to consume predictive insights for business process optimization and drive value. Use cases include propensity to buy, lead conversion, propensity to churn, and more.
  • Operationalize models and inferences easily in Salesforce.Data 360 simplifies the consumption of results from business processes and drives value.
  • Eliminate tedious, costly, and error-prone Extract, Transform, and Load (ETL) jobs from Databricks using a zero-copy approach to data. This approach reduces costs and improves efficiencies.
  • Integrate Vertex AI models and get predictions in Salesforce. Use Flow, a workflow automation suite, to enable AI-driven decision-making that can evolve based on real-time updates to data.

To use a Databricks model with Salesforce:

  • Access your Data 360 data in Databricks to build, train, and deploy a model.
  • Connect your Databricks model with Data 360 to consume the inferences for predictions and insights in various workflows across Salesforce.
Diagram showing data flow between Databricks and Salesforce
  • Set Up Your Data in Databricks
    Access Salesforce data in your Databricks notebook using a Python connector. The user-friendly interface lets you quickly execute queries against data in Data 360 so that you can extract the data that you need into Python.
  • Set Up an Endpoint in Databricks
    Control the access to your data by setting up an endpoint connection between Databricks and Data 360.
  • Connect a Databricks Model
    To consume predictions in Salesforce, connect your Databricks model with Data 360 and define the prediction criteria for your use case.