Profile: Model Creator
Model creators are responsible for creating the machine-learning (ML) models that power Squirro’s AI applications.
While ML models can be created outside of Squirro and imported into the platform, Squirro’s AI Studio provides a no-code interface for creating and training models. While it helps to have prior experience with machine learning, model creators do not need a technical background in machine learning to use the AI Studio.
This page provides an overview of the Model Creator role and links to relevant parts of Squirro’s documentation.
The Model Creator role focuses explicitly on creating models within Squirro. For general-purpose data scientist and analyst activities, see the Data Scientist role.
As a model creator, you are responsible for creating and training the machine-learning (ML) models that power Squirro’s AI applications.
The primary tool you’ll work with is the Squirro AI Studio, a no-code interface for creating and training ML models.
Reference: Learn more by browsing the AI Studio documentation.
Importing Existing Models#
If you have created a model outside of Squirro that you would like to import, see the Data Scientist profile for an overview of the import process.
The Squirro AI Studio is a no-code interface for creating and training ML models that follows a five-step process outlined below:
The five steps to creating a model using AI Studio, with relevent documentation linked, are:
Candidate Set: Create a candidate set of documents that will be used to train the model.
Ground Truth: Create a ground truth set of documents that will be used to train the model.
Model Training: Create and train the model. The model can be trained using a variety of algorithms and parameters.
Validation: Validate the model using a validation set of documents.
Publish: Publish the model to make it available for use in Squirro AI applications.
The Squirro Academy offers a dedicated AI Studio Model Creator Certification Course.