{"id":17438263,"url":"https://github.com/sandk21/detection_faux_billets","last_synced_at":"2026-04-03T23:39:02.005Z","repository":{"id":257943828,"uuid":"872901690","full_name":"Sandk21/detection_faux_billets","owner":"Sandk21","description":"Algorithme de détection de faux billets selon leurs dimensions géométriques et application web pour générer les prédictions ","archived":false,"fork":false,"pushed_at":"2024-11-14T08:59:02.000Z","size":63081,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-02-02T03:42:27.930Z","etag":null,"topics":["data-analysis","data-science","data-visualization","machine-learning","pandas","python","scipy","sklearn","streamlit"],"latest_commit_sha":null,"homepage":"","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/Sandk21.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-10-15T09:14:01.000Z","updated_at":"2024-11-14T08:59:07.000Z","dependencies_parsed_at":"2024-10-17T03:54:32.480Z","dependency_job_id":null,"html_url":"https://github.com/Sandk21/detection_faux_billets","commit_stats":null,"previous_names":["sandk21/detection_faux_billets"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sandk21%2Fdetection_faux_billets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sandk21%2Fdetection_faux_billets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sandk21%2Fdetection_faux_billets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sandk21%2Fdetection_faux_billets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Sandk21","download_url":"https://codeload.github.com/Sandk21/detection_faux_billets/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245955851,"owners_count":20699988,"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","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":["data-analysis","data-science","data-visualization","machine-learning","pandas","python","scipy","sklearn","streamlit"],"created_at":"2024-10-17T12:05:15.374Z","updated_at":"2025-12-30T20:32:02.740Z","avatar_url":"https://github.com/Sandk21.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"![image](https://github.com/user-attachments/assets/62406732-8067-4bc2-9d96-440062cd4ddc)\n\n# Détection automatique de faux billets\n\n[Lien vers l'application finalisée](https://detectionfauxbillets-eerqtpxtxetqwjdsg6l7jy.streamlit.app/)\n\nDes fichiers csv sont mis à disposition dans ce [dossier](https://github.com/Sandk21/detection_faux_billets/tree/main/data).\n\n## Contexte du projet\nL'**Organisation Nationale de Lutte contre le Faux-Monnayage (ONCFM)**, organisme public, a pour mission de développer des méthodes avancées d’**identification des contrefaçons de billets** en euros.\n\nDans ce cadre, l'ONCFM souhaite développer un algorithme pour analyser les **caractéristiques géométriques des billets** \net déterminer, sur la base de ces paramètres, s’il s’agit de billets authentiques ou falsifiés.\n\n## Objectifs\nDévelopper un **algorithme de machine learning** capable de distinguer les billets authentiques des contrefaçons en s'appuyant sur leurs caractéristiques géométriques.\nMettre cet algorithme à disposition des professionnels bancaires via une **application**, facilitant ainsi la détection des faux billets.\n\n## Données\n![{6FEDE686-7D5E-43B2-93CC-BBE781973EF4}](https://github.com/user-attachments/assets/7cdb97e1-1646-4501-a324-b4a123c523bc)\n\n## Raodmap\n![{930F8378-D2FC-4F71-802A-5AD4794F3836}](https://github.com/user-attachments/assets/c028a3f1-eaaa-4f3b-94ec-919e3ddbec74)\n![{4DC49935-A7F1-4993-A09F-295CCA2A369E}](https://github.com/user-attachments/assets/9e33dfdd-d2be-42c8-8d1f-aae855f9ca36)\n\n\n## Résultats\n![image](https://github.com/user-attachments/assets/7605f6ef-f2c7-4909-9acd-7679cfd5a93d)\n\nModèle de classification retenu : la régression logistique a permis d'obtenir les meilleurs performance de classification pour les différentes métrics utilisées\n(recall, score f1 en particulier)\n![{098798EE-EA65-42A8-9FA4-3DFC36DFE992}](https://github.com/user-attachments/assets/813632e1-c8e8-446e-ab72-ef80d90a65e3)\n\n## Livrables\nModèle de régression linéaire stocké au format pickle\nApplication de détection de faux billets avec streamlit\n![image](https://github.com/user-attachments/assets/1771ad1c-b426-41e6-ae36-cdddd42e6781)\n\n![image](https://github.com/user-attachments/assets/1ad8388c-2664-420e-a0e6-203cb9fdcee0)\n\n![image](https://github.com/user-attachments/assets/86e3db4d-9e8d-44ce-915c-555214368fa9)\n\n\n## \n\u003eLe projet a été réalisé dans le cadre d'une formation de Data Analyst avec OpenClassroom\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsandk21%2Fdetection_faux_billets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsandk21%2Fdetection_faux_billets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsandk21%2Fdetection_faux_billets/lists"}