Salesforce Data Cloud Bring Your Own Model

**Overview**
Create machine learning models using both Databricks and Salesforce data to improve your business outcomes. Combine the power of Databricks for model training and serving to power machine learning related workloads with your Salesforce data in this simple, easy to use accelerator.

This accelerator uses the new BYOM integration between Salesforce and Databricks. This collaboration enables data scientists and machine learning engineers to seamlessly leverage the best of both worlds: the robust customer data and business capabilities in Salesforce and the advanced analytics and AI capabilities of Databricks.

**Use cases**
- Recommend products to customers based on what they've purchased or viewed in the past
- Predict whether a given lead will convert to a sale
- Determine likelihood of escalation of a use case
- Predict whether a given customer is likely to churn
- Forecast late payments
- and so many more!

**Product details**
This solution accelerator will help you:

- set up the required objects in Salesforce
- query data from Salesforce to set up a feature table in Unity Catalog
- build and train a model in Databricks using MLflow for experiment tracking
- manage model lifecycle using Unity Catalog
- deploy a model to a Databricks serving endpoint
- configure the serving endpoint in Einstein Studio on Salesforce
- score a dataset in Salesforce using the model

You can use this as a starting point for building your own models with Salesforce data in Databricks! For more details, refer to the embedded notebooks, or check out our [blog post](https://www.databricks.com/blog/introducing-salesforce-byom-databricks).

**Additional Insights**
You can find out more about the Bring Your Own Model integration in the [Salesforce Documentation](https://help.salesforce.com/s/articleView?id=sf.c360_a_bring_your_own_model.htm&type=5).