Model cards with vetiver for transparent, responsible reporting
This workflow demo highlights a suggested framework for organizing and presenting the essential facts about a deployed machine learning model, using the vetiver packages for both R and Python and model cards.
Good documentation helps us make sense of software, know when and how to use it, and understand its purpose. The same can be true of documentation or reporting for a deployed model, but it can be hard to know where to start.
In this demo, Julia Silge highlights:
- How to get started with your first model card
- How a model card fits in with model monitoring
- How to use Posit Team to author and publish your model card
Helpful links:
- Paper “Model Cards for Model Reporting” (Mitchell et al. 2019)
- GitHub Repo for this example
- Q&A Recording
- Positron, a next-generation data science IDE
- Vetiver package
- Quarto Dashboards
- Pins package
- ML Fairness Case Study
- Positron, available as a preview feature on Posit Workbench
- Posit Publisher Extension
We host these Workflow Demos the last Wednesday of every month, and you can add them to your calendar with this link: https://www.addevent.com/event/Eg16505674
Tags:
vetiver