{"id":28870996,"url":"https://github.com/mohammedsaim-quadri/ann-classification-churn","last_synced_at":"2026-06-20T04:31:13.941Z","repository":{"id":290628720,"uuid":"975090774","full_name":"MohammedSaim-Quadri/ANN-Classification-Churn","owner":"MohammedSaim-Quadri","description":"Predict customer churn using a deep learning ANN model deployed with Streamlit. Interactive UI, real-time predictions, and model trained on a real-world banking dataset.","archived":false,"fork":false,"pushed_at":"2025-04-29T19:52:29.000Z","size":418,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-30T04:11:14.337Z","etag":null,"topics":["ann","churn-prediction","classification","deployment","machine-learning","streamlit-webapp","ui"],"latest_commit_sha":null,"homepage":"https://ann-classification-churn-3kq5m6c96mw9lz48bszpqv.streamlit.app/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MohammedSaim-Quadri.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"zenodo":null}},"created_at":"2025-04-29T19:10:13.000Z","updated_at":"2025-04-29T19:53:57.000Z","dependencies_parsed_at":"2025-04-29T20:25:50.600Z","dependency_job_id":"054c5470-24bd-43a3-8501-5fe47a921e78","html_url":"https://github.com/MohammedSaim-Quadri/ANN-Classification-Churn","commit_stats":null,"previous_names":["mohammedsaim-quadri/ann-classification-churn"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/MohammedSaim-Quadri/ANN-Classification-Churn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MohammedSaim-Quadri%2FANN-Classification-Churn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MohammedSaim-Quadri%2FANN-Classification-Churn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MohammedSaim-Quadri%2FANN-Classification-Churn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MohammedSaim-Quadri%2FANN-Classification-Churn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MohammedSaim-Quadri","download_url":"https://codeload.github.com/MohammedSaim-Quadri/ANN-Classification-Churn/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MohammedSaim-Quadri%2FANN-Classification-Churn/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34557551,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-20T02:00:06.407Z","response_time":98,"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":["ann","churn-prediction","classification","deployment","machine-learning","streamlit-webapp","ui"],"created_at":"2025-06-20T14:12:44.033Z","updated_at":"2026-06-20T04:31:13.923Z","avatar_url":"https://github.com/MohammedSaim-Quadri.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ANN-Based Customer Churn Classification\n\nA Streamlit web application that predicts the likelihood of a customer churning using an Artificial Neural Network (ANN) model trained on the **Churn Modelling Dataset**. The app enables interactive input of customer features to instantly obtain predictions based on a pre-trained deep learning model.\n\n🔗 **Live App**: [Visit the Streamlit App](https://ann-classification-churn-3kq5m6c96mw9lz48bszpqv.streamlit.app/)\n\n---\n\n## Project Overview\n\nThis project addresses the business-critical problem of **customer churn prediction**. It uses a fully connected ANN trained on a dataset of bank customers. The app allows users to enter various customer attributes like age, credit score, and account balance, and outputs the probability of churn in real time.\n\n---\n\n## Model Details\n\n- **Architecture**: Fully Connected ANN with multiple Dense layers\n- **Framework**: TensorFlow / Keras\n- **Objective**: Binary classification (Churn or Not Churn)\n- **Preprocessing**:\n  - Label Encoding for Gender\n  - One-Hot Encoding for Geography\n  - Standard Scaling for numerical features\n\n---\n\n## Features\n\n- Real-time prediction via interactive UI\n- Trained deep learning model (`.h5` file)\n- Cleaned and preprocessed dataset (`Churn_Modelling.csv`)\n- Pickled encoders and scaler for deployment\n- Streamlit frontend with sliders, input fields, and dropdowns\n\n---\n\n## Repository Structure\n```bash\nann-classification-churn/\n│ ├── app.py # Streamlit app script\n├── churn_model.h5 # Trained ANN model\n├── Churn_Modelling.csv # Dataset used for training\n├── experiments.ipynb # Model building and tuning experiments\n├── prediction.ipynb # Final prediction pipeline notebook\n├── label_encoder_gender.pkl # Label Encoder for Gender\n├── ohe_geo.pkl # One-Hot Encoder for Geography\n├── scaler.pkl # Standard Scaler\n├── requirements.txt # Python dependencies\n├── LICENSE # License file\n└── README.md # You're here!\n\n```\n\n---\n\n## How to Run Locally\n\n### 1. Clone the Repo\n\n```bash\ngit clone https://github.com/your-username/mohammedsaim-quadri-ann-classification-churn.git\ncd mohammedsaim-quadri-ann-classification-churn\n```\n\n### 2.Set Up Environment\nRecommend using a virtual environment:\n```bash\npython -m venv venv\nsource venv/bin/activate  # or venv\\Scripts\\activate on Windows\n```\n\n### 3.Install Dependencies\n```bash\npip install -r requirements.txt\n```\n\n### 4. Run the App\n```bash\nstreamlit run app.py\n```\n\n---\n\n## Dataset\nThe model is trained on the Churn Modelling Dataset which includes:\n- Demographic and financial details of 10,000+ bank customers\n- Target: Exited (1 = churned, 0 = retained)\n\nFeatures used:\n- Credit Score\n- Geography\n- Gender\n- Age\n- Tenure\n- Balance\n- Num of Products\n- Has Credit Card\n- Is Active Member\n- Estimated Salary\n\n---\n\n## Demo Screenshot\n![App Screenshot](./demo.png)\n\n---\n\n## Deployment\nThe model is deployed using Streamlit Community Cloud with all encoders and scalers serialized via pickle.\n\n🔗 [Visit the Streamlit App](https://ann-classification-churn-3kq5m6c96mw9lz48bszpqv.streamlit.app/)\n\n---\n\n## License\nThis project is licensed under the terms of the GNU License. See the LICENSE file for details.\n\n---\n👨‍💻 Author\nMohammed Saim Ahmed Quadri\n📫 [LinkedIn](https://www.linkedin.com/in/msaquadri)\n📧 mohammedsaimquadri@gmail.com\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmohammedsaim-quadri%2Fann-classification-churn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmohammedsaim-quadri%2Fann-classification-churn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmohammedsaim-quadri%2Fann-classification-churn/lists"}