Creating custom algorithms

Complete the following steps to create a custom algorithm.

To create a custom algorithm:

  1. Click the Oracle icon Image of the application navigation button. Use it to access the different parts of Oracle Unity. in the bottom-right corner to open the navigation menu.
  2. Select Intelligence workbench.
  3. Click the Algorithms tab.
  4. Click Create algorithm. The Create algorithm page will display.

    5. An image of the Intellgence workbench page

Step 1: Define algorithm details

Enter the details for the algorithm.

To define the algorithm details:

  1. Enter the algorithm details.

    2. An imag of the details section for an algorithm

    • Name: Enter a name for the algorithm.

    • Description: Optionally, enter a description.

    • Family: Use the drop-down list to select the family the algorithm belongs to.

    • Purpose: Select the purpose of the algorithm.

      • If the algorithm will only be used for scoring models, select Scoring.

      • If the algorithm will be used for scoring and training models, select Training and Scoring.

  2. Confirm the details and click Code to go to the next section.

Step 2: Algorithm code

To define the algorithm code, you will need to do the following:

  • Import the algorithm code as a docker image.

  • Upload a JSON file that will be loaded during scoring.

To define the algorithm code:

  1. Enter the details for the docker image.

    2. An image of the code section for an algorithm

    • Docker image URL: Enter the URL of the Oracle Cloud Infrastructure Registry (OCIR) or public registry that stores the docker image.

    • Username: Enter the required username to access the URL.

    • Password: Enter the required password to access the URL.

  2. Click Drag and Drop + to select a model file in JSON format or drag the required file to Attach a JSON file (Required).

    3. An image of the JSON file section for an algorithm

  3. Review the code details and click Attributes to go to the next section.

Step 3: Algorithm attributes

You will need to do the following to define algorithm attributes:

  • Select attributes as inputs that the algorithm will use for training/scoring.

  • Select attributes that will be used as outputs for algorithm scoring.

To define inputs:

  1. Enter the details for the input attribute.

    An image of the Algorithm inputs section

    1. Attribute name: Enter the attribute name.

    2. Data type: Select the data type for the attribute. Learn more about Data types.

    3. Description: Enter a description.

  2. Click Add An image of the add icon to create the attribute input.

    3. An image of the Add button

  3. Continue creating all the required attribute inputs.

To define outputs:

  1. Enter the details for the output attribute.

    An image of the Algorithm outputs section

    1. Attribute name: Enter the attribute name.

    2. Data type: Select the data type for the attribute. Learn more about Data types.

    3. Key attribute: Select if the output attribute is a key attribute.

    4. Description: Enter a description.

  2. Click Add An image of the add icon to create the attribute output.

    3. An image of the Add button

  3. Continue creating all the required attribute outputs.

  4. When done creating all the inputs and outputs, click Configuration to go to the next section.

Step 4: Algorithm parameters and Hyperparameters

  • The algorithm parameters you configure allow you to tweak the model according to the required content at any point in time. For example, you can configure a lookback window and provide several options with lookback windows of differing number of days.

  • Hyperparameters allow you to configure adjustable parameters that can be tuned into order to get a model with optimal performance. For example, you can configure the hyperparameters such as learning rate or tuning rate.

To configure algorithm parameters:

  1. Enter the details for the algorithm parameter.

    An image of the Algorithm parameters section

    1. Parameter name: Enter a name for the parameter.

    2. Display type: Select how to display the options for the parameter.

      • Drop-down: Create a drop-down list that allows you to select from a pre-defined list of options.

      • Text field: Provide an input field that allows you to input any value while creating a model.

    3. Data type: Select the data type for the parameter. Learn more about Data types.

    4. Allowable values: Enter the permitted values for the parameters separated by commas.

    5. Default value: Enter the default value for configuring the parameter.

  2. Click Add An image of the add icon to create the algorithm parameter.

    3. An image of the Add button

  3. Continue creating all the required algorithm parameters.

To configure hyperparameters:

  1. Enter the details for the hyperparameter.

    An image of the Hyperparameters section

    1. Hyperparameter name: Enter the name for the hyperparameter.

    2. Level: Enter the numeric value that defines the level of the hyperparameter. For example, if you configure a learning rate, the level value determines the step size at each iteration.

  2. lick Add An image of the add icon to create the hyperparameter.

    3. An image of the Add button

  3. Continue creating all the required hyperparameters.

  4. Confirm all the created parameters and click Save.

After saving the custom algorithm, it will be added to the available algorithms in the Algorithms section of the Intelligence workbench page.

Learn more

Viewing algorithms

data science, data science model, analyze data