Nelsonchris1/ML-explainability-app
This is a web app built for easy explainability of machine learning models without writing any code in order to explain easily to non-technicals and stakeholders.
This tool helps you understand and explain why a machine learning model makes certain predictions, especially for non-technical stakeholders. You simply upload your model's data, and it provides visualizations and explanations without any coding. It's ideal for data scientists, machine learning engineers, or business analysts who need to communicate model behavior clearly to their teams or clients.
No commits in the last 6 months.
Use this if you need to quickly generate explanations for your supervised machine learning models to share with non-technical audiences, without writing any code.
Not ideal if you need to explain deep learning models or require highly customized, code-based explanations.
Stars
20
Forks
7
Language
Python
License
—
Category
Last pushed
Jan 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Nelsonchris1/ML-explainability-app"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shap/shap
A game theoretic approach to explain the output of any machine learning model.
mmschlk/shapiq
Shapley Interactions and Shapley Values for Machine Learning
iancovert/sage
For calculating global feature importance using Shapley values.
predict-idlab/powershap
A power-full Shapley feature selection method.
aerdem4/lofo-importance
Leave One Feature Out Importance