{"id":25117934,"url":"https://github.com/retkowsky/interpretml","last_synced_at":"2025-08-31T22:09:30.104Z","repository":{"id":113063996,"uuid":"209305624","full_name":"retkowsky/InterpretML","owner":"retkowsky","description":"Démonstration Azure InterpretML","archived":false,"fork":false,"pushed_at":"2019-09-26T07:51:15.000Z","size":864,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-07-18T18:26:33.469Z","etag":null,"topics":["azureml","interpretml","notebook"],"latest_commit_sha":null,"homepage":"https://github.com/Microsoft/interpret","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/retkowsky.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2019-09-18T12:41:57.000Z","updated_at":"2019-09-26T07:51:17.000Z","dependencies_parsed_at":null,"dependency_job_id":"7e568481-a14c-4ec4-8d01-c5ff0b9e0628","html_url":"https://github.com/retkowsky/InterpretML","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/retkowsky/InterpretML","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retkowsky%2FInterpretML","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retkowsky%2FInterpretML/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retkowsky%2FInterpretML/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retkowsky%2FInterpretML/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/retkowsky","download_url":"https://codeload.github.com/retkowsky/InterpretML/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retkowsky%2FInterpretML/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273046577,"owners_count":25036199,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-31T02:00:09.071Z","response_time":79,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["azureml","interpretml","notebook"],"created_at":"2025-02-08T03:37:57.945Z","updated_at":"2025-08-31T22:09:30.057Z","avatar_url":"https://github.com/retkowsky.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# InterpretML\nDémonstration Azure InterpretML\n\nhttps://github.com/Microsoft/interpret\n\nInterpretML is an open-source python package for training interpretable models and explaining blackbox systems. \nInterpretability is essential for:\n- Model debugging - Why did my model make this mistake?\n- Detecting bias - Does my model discriminate?\n- Human-AI cooperation - How can I understand and trust the model's decisions?\n- Regulatory compliance - Does my model satisfy legal requirements?\n- High-risk applications - Healthcare, finance, judicial, ...\n\nHistorically, the most intelligible models were not very accurate, and the most accurate models were not intelligible. \nMicrosoft Research has developed an algorithm called the Explainable Boosting Machine (EBM)* which has both high accuracy and \nintelligibility. \n\nEBM uses modern machine learning techniques like bagging and boosting to breathe new life into traditional \nGAMs (Generalized Additive Models). \nThis makes them as accurate as random forests and gradient boosted trees, and also enhances their intelligibility and editability.\n\nIn addition to EBM, InterpretML also supports methods like LIME, SHAP, linear models, partial dependence, decision trees, and rule lists. \nThe package makes it easy to compare and contrast models to find the best one for your needs.\n\n\nSerge Retkowsky | serge.retkowsky@microsoft.com | https://www.linkedin.com/in/serger/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fretkowsky%2Finterpretml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fretkowsky%2Finterpretml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fretkowsky%2Finterpretml/lists"}