{"id":15968894,"url":"https://github.com/miguellopezvirues/telecom_churn","last_synced_at":"2026-04-12T09:49:09.214Z","repository":{"id":255931307,"uuid":"853909170","full_name":"MiguelLopezVirues/telecom_churn","owner":"MiguelLopezVirues","description":"Development and deployment of ML solution for a Telecom Churn business case.","archived":false,"fork":false,"pushed_at":"2024-09-08T19:49:56.000Z","size":24310,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-10T00:19:34.183Z","etag":null,"topics":["aws","churn-prediction","deployment","docker","end-to-end","machine-learning","python"],"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/MiguelLopezVirues.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":"2024-09-07T21:49:51.000Z","updated_at":"2024-09-08T19:51:25.000Z","dependencies_parsed_at":"2024-10-30T04:02:31.373Z","dependency_job_id":null,"html_url":"https://github.com/MiguelLopezVirues/telecom_churn","commit_stats":null,"previous_names":["miguellopezvirues/telecom_churn"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MiguelLopezVirues%2Ftelecom_churn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MiguelLopezVirues%2Ftelecom_churn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MiguelLopezVirues%2Ftelecom_churn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MiguelLopezVirues%2Ftelecom_churn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MiguelLopezVirues","download_url":"https://codeload.github.com/MiguelLopezVirues/telecom_churn/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247192522,"owners_count":20899118,"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":["aws","churn-prediction","deployment","docker","end-to-end","machine-learning","python"],"created_at":"2024-10-07T19:04:25.154Z","updated_at":"2026-04-12T09:49:09.148Z","avatar_url":"https://github.com/MiguelLopezVirues.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# End to end ML solution for Telecom Churn prediction\nThis end to end project consists on providing a solution for a churn business case given a telecom churn dataset. Value is provided through:\n- Data analysis: Understanding the root of the problem and providing actionable insights.\n- ML model evaluation and configuration: Proposing several ML models and evaluating them, then proposing on the configuration of batch and real-time inference.\n- Deployment of the ML solution: Containerizing the selected ML model to be deployed as a real-time inference solution in AWS Elasticbeanstalk.\n\n## Install\nTo run the projects file, download it and run `pip install -r requirements.txt` for the home directory. Otherwise, ``Pipfile`` and ``Pipfile.lock`` are available inside `\\Deployment`\n\n## Using the application\nTo test the project, run `python predict_request-test.py`. It will make a request to the AWS application and return the churn prediction {0,1} for the example written on the script.\n\n## Contents\n- ``Churn_Business_Case.md``: Summary description of the business case for telecom churn.\n- ``requirements.txt``\n- ``\\Development``\n    - ``churn_all.csv``: Source dataset\n    - ``Churn_ML_model_evaluation.ipynb``: Notebook with the exploratory data analysis and insights, evaluation and selection of the ML model, proposal of inference configuration and final recommendations.\n- ``\\Deployment``\n    - ``train.py``: Data import from the source dataset, data processing and training of the selected model configuration from the Churn_ML_model_evaluation notebook.\n    - ``predict_request.py``: Model loading and prediction, served as a flask application. Receives a JSON file with the variables for a single customer. Returns either 1 or 0 as a churn prediction.\n    - ``predict_request-test.py``: Test of the request with the information of a single customer.\n    - ``model.pkl``\n    - ``category_group_map.pkl``: Category mapping automatically engineered through training, called by predict_request to preprocess the customer data.\n    - ``Pipfile and Pipfile.lock``\n    - ``Dockerfile``\n\n## Technologies used\n\nPython, Jupyter notebook, Pipenv, Docker, AWS Elasticbeanstalk","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmiguellopezvirues%2Ftelecom_churn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmiguellopezvirues%2Ftelecom_churn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmiguellopezvirues%2Ftelecom_churn/lists"}