Fiddler’s industry-first model analytics tool, called Slice and Explain, allows you to perform an exploratory or targeted analysis of model behavior.
- Slice — Identify a selection, or slice, of data. Or, you can start with the entire dataset for global analysis.
- Explain — Analyze model behavior on that slice using Fiddler’s visual explanations and other data insights.
Slice and Explain is designed to help data scientists, model validators, and analysts drill down into a model and dataset to see global, local, or instance-level explanations for the model’s predictions.
Slice and Explain can help you answer questions like:
- What are the key drivers of my model output in a subsection of the data?
- How are the model inputs correlated to other inputs and to the output?
- Where is my model underperforming?
- How is my model performing across the classes in a protected group?
Access Slice and Explain from the Analyze tab for your model. Slice and Explain currently support all tabular models.
For details on how to use Fiddler Analytics through our interface check the Analytics Page on our UI Guide
Model performance evaluation is one of the key tasks in the ML model lifecycle. A model's performance indicates how successful the model is at making useful predictions on data.
For details on how to use Fiddler Evaluation through our interface check the Evaluation Page on our UI Guide
Updated about 2 months ago