serval-uni-lu/confetti
Counterfactual explanations for multivariate time series classifiers.
This project helps data scientists and machine learning engineers understand why a deep learning model classified a multivariate time series in a certain way. By inputting your time series data and a classification model, it outputs "counterfactual explanations." These explanations show the smallest changes to your original data that would flip the model's classification, helping you gain trust and insights into the model's decision-making.
Use this if you need to explain the reasoning behind a deep learning model's classification of complex time series data, for example, in medical diagnostics, financial forecasting, or industrial monitoring.
Not ideal if you are working with non-time series data, or if your primary goal is to improve model accuracy rather than understand its decisions.
Stars
11
Forks
—
Language
Python
License
MIT
Last pushed
Dec 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/serval-uni-lu/confetti"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...