- Getting Started
- Administration
- Manage Sources and Datasets
- Understanding the data structure and permissions
- Create a data source in the GUI
- Uploading a CSV file into a source
- Create a new dataset
- Multilingual sources and datasets
- Enabling sentiment on a dataset
- Amend a dataset's settings
- Delete messages via the UI
- Delete a dataset
- Export a dataset
- Using Exchange Integrations
- Preparing Data for .CSV Upload
- Model Training and Maintenance
- Understanding labels, entities and metadata
- Label hierarchy and best practice
- Defining your taxonomy objectives
- Analytics vs. automation use cases
- Turning your objectives into labels
- Building your taxonomy structure
- Taxonomy design best practice
- Importing your taxonomy
- Overview of the model training process
- Generative Annotation (NEW)
- Understanding the status of your dataset
- Model training and labelling best practice
- Training with label sentiment analysis enabled
- Train
- Introduction to 'Refine'
- Precision and recall explained
- Precision and recall
- How does Validation work?
- Understanding and improving model performance
- Why might a label have low average precision?
- Training using 'Check label' and 'Missed label'
- Training using Teach label (Refine)
- Training using Search (Refine)
- Understanding and increasing coverage
- Improving Balance and using 'Rebalance'
- When to stop training your model
- Using Analytics & Monitoring
- Automations and Communications Mining
- FAQs and More
Models
A machine learning model is essentially a mathematical representation of a real-world process. To create machine learning models, you need to provide machine learning algorithms with training data from which they can learn.
The platform uses a number of machine learning models (both supervised and unsupervised) in order to interpret, understand and apply labels to your data. We often use the term 'model' in our platform and our documentation to refer collectively to these models working behind the scenes.
Every dataset has a 'model' associated with it, that is trained as users review messages within the platform. As the model trains, it learns and improves, enabling it to make better predictions for labels and entities.
Models can be saved and versioned. This means that when users set up an automation stream, they can select a specific version of the model and can be confident in the performance of that version for the label in question. This gives users determinism when it comes to creating automations or using the data for analytics in downstream applications. For more information, see the models section.