Custom data science models

You can create custom data science models from the Intelligence workbench page.

Notes:

To enable this feature, please create a service request at My Oracle Support.
Custom algorithms that you use for custom models must be in Python. Additional supported languages are planned for future Unity releases.

Custom data science models explained

Oracle Unity allows you to create custom data science models and algorithms that meet your specific needs. Learn more about Data science algorithms.

You can leverage custom models in the following ways:

Bring your own score: The training and scoring values are calculated externally. You can import the scoring values for use with the data in Oracle Unity.
Bring your own inference: Training values are calculated externally. You can import the training values into Oracle Unity to be used for calculating scoring values.
Bring your own model: The trained model is imported into Oracle Unity. Re-training and scoring values are then calculated within Oracle Unity.

You have the option of creating a custom algorithm for a custom data science model. Learn more about Creating custom algorithms.

When creating custom data science models, you will need to define the following parameters for the model:

Algorithm: The algorithm is the piece of code that runs the model. You have the option of selecting a ready-to-use algorithm or a custom algorithm. Learn more about Creating custom algorithms.
Queries: The queries selected for the model generate a dataset for model training and scoring.
Inputs: The inputs are query attributes from the Unity data model that are used for model training and scoring. You can't make changes to model inputs.
Outputs: The outputs are data objects and attributes from the Unity data model that are used to store the output values of the model.

To create and use a custom data science model, you will need to do the following:

If you need to create a custom algorithm for the custom model, follow the steps for Creating custom algorithms. Otherwise, proceed to the next step.
Follow the steps for Creating custom data science models.
After creating the model, follow the steps for Running training and scoring jobs.

After the model runs and creates output values, you can do the following:

Access data for custom data science models to review the values in the output attributes.
Learn more about Using data science data for the specific needs of your organization.
If needed, you can review the data science model details.