Skip to content
/ xai-app Public

Prototype for an Interpretable Machine Learning model in production

Notifications You must be signed in to change notification settings

sahbic/xai-app

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

xai-app

Prototype for an Interactive & Interpretable Machine Learning model in production

It is built using:

  • React.js
  • Flask
  • Jupyter Notebook

Preview

image

Motivation

For every decision made with an ML model, we should be able to have clues about why this decision was made. We trust human decisions once we understand them and when they are based on facts and thorrow analysis. It should be the same for Machine Learning Models.

This app allows to interact with Machine Learning models to better understand the output.

It uses the local interpretabilty method of SHAP values to explain why a decision was made, and highlight what are the features that are pushing the prediction value up or down.

"Interpretability is the degree to which a human can understand the cause of a decision" Miller, Tim

About

Prototype for an Interpretable Machine Learning model in production

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published