Crisp-Unimib/MERLIN

MERLIN is a global, model-agnostic, contrastive explainer for any tabular or text classifier. It provides contrastive explanations of how the behaviour of two machine learning models differs.

37
/ 100
Emerging

When you have two machine learning models for tabular or text data and need to understand exactly how their decision-making differs, this tool helps. You provide the raw data and each model's predictions, and it outputs clear, natural language explanations of what criteria one model uses that the other doesn't, and vice-versa. This is for data scientists, machine learning engineers, or domain experts who need to compare and explain model behavior.

No commits in the last 6 months.

Use this if you need to compare two machine learning classifiers and get specific, human-readable explanations about why they make different decisions on the same kind of data.

Not ideal if you only have one model and just need a general explanation of its behavior, or if you are comparing models on image or audio data.

model-comparison explainable-ai machine-learning-auditing text-classification-analysis tabular-data-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

19

Forks

5

Language

Python

License

MIT

Last pushed

Sep 15, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Crisp-Unimib/MERLIN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.