Library/AIX360Forked

Trusted-AI/AIX360

AIX360

Interpretability and explainability of data and machine learning models

View on GitHub↗Upstream Trusted-AI/AIX360↗

Builder

Trusted-AI

Trusted-AI • individual

Stars

1,772

Using upstream star count

Forks

328

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Jul 11, 2019

Project creation date

README Summary

AIX360 is a comprehensive Python toolkit developed by IBM Research for interpretability and explainability of datasets and machine learning models. The library provides a wide range of algorithms including post-hoc explanation methods, directly interpretable models, and different data explanation techniques. It supports various model types and offers both local and global explanation capabilities with practical tutorials and examples.

AI Dev Skills

Unmapped

Tags

Explainable AI (XAI)Model InterpretabilityLIME (Local Interpretable Model-agnostic Explanations)SHAP (SHapley Additive exPlanations)Counterfactual ExplanationsFeature AttributionPost-hoc Explanation MethodsModel-Agnostic InterpretabilityGlobal Model ExplanationLocal Model ExplanationSurrogate Model TechniquesAdversarial DebiasingFairness in Machine LearningBias Detection and MitigationRegulatory ComplianceImageAlgorithmic TransparencyRegulatory Compliance ReportingFeature Importance AnalysisAI GovernanceTrustworthy AI DevelopmentGovernmentAI SafetyInsuranceJupyter NotebooksTrustworthy AIAI EthicsTabularModel Debugging and ValidationFinancial ServicesRisk Assessment ExplanationResponsible AITextLegal TechOn-premiseSelf-hostedCloud APIModel Decision ExplanationHealthcarePython

Taxonomy

AI Trends

AI Safety Trustworthy AI Responsible AI AI Governance AI Ethics

Deployment Context

Self-hosted On-premise Cloud API Jupyter Notebooks

Industries

Healthcare Financial Services Legal Tech Insurance Government Regulatory Compliance

Modalities

Tabular Text Image

Skill Areas

Use Cases

Model Decision Explanation Regulatory Compliance Reporting Bias Detection and Mitigation Feature Importance Analysis Model Debugging and Validation Trustworthy AI Development Algorithmic Transparency Risk Assessment Explanation

Recent Activity

Updated 26 days ago

7 Days

30 Days

90 Days

Quality

research

Quality: high
Maturity: research

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created: Jul 11, 2019
Forked: Mar 22, 2026
Your last push: 26 days ago
Upstream last push: 26 days ago
Tracked since: Mar 18, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…