Predictive models continue to increase in both accuracy and complexity. These models can be difficult to interpret and trust, and businesses need to be aware of how these models work before they can be deployed. Model interpretation is an important part of the data science workflow. We discuss some of the tools and techniques that can be used to validate and understand black box models.
Share this page
Validating the black box - Model interpreters
This briefing note discusses some of the tools and techniques that can be used to validate and understand black box models.
Eoin O'Baoighill, Eamonn Phelan
These Cookies are used by us or third-party service providers to analyze how the Sites are used and how they are performing. We use the following service providers and you can learn more about their privacy policies and how to opt-out of their cookies by clicking on these links:
These Cookies are necessary for you to access and navigate our sites.
We use ‘social buttons’ to enable our users to share or bookmark web pages. These are buttons for third party social media sites. We use the following service providers and you can learn more about their privacy policies and how to opt-out of their cookies by clicking on these links: