{"id":29035574,"url":"https://github.com/v41bh4vr4jput/churm-prediction","last_synced_at":"2025-06-26T12:10:57.774Z","repository":{"id":299212810,"uuid":"1001682707","full_name":"V41BH4VR4JPUT/Churm-Prediction","owner":"V41BH4VR4JPUT","description":"A machine learning-powered dashboard for predicting customer churn. This project covers everything from data preprocessing to model building, evaluation, and a Streamlit-based dashboard for visual insights and predictions.","archived":false,"fork":false,"pushed_at":"2025-06-15T10:46:47.000Z","size":7094,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-15T11:35:35.962Z","etag":null,"topics":["churn-prediction","ensemble-model","logistic-regression","random-forest","streamlit","xgboost"],"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/V41BH4VR4JPUT.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,"zenodo":null}},"created_at":"2025-06-13T20:11:31.000Z","updated_at":"2025-06-15T10:46:50.000Z","dependencies_parsed_at":"2025-06-15T11:35:40.623Z","dependency_job_id":"e8fbdf0b-9edc-4ed0-8c41-02d5bbb38632","html_url":"https://github.com/V41BH4VR4JPUT/Churm-Prediction","commit_stats":null,"previous_names":["v41bh4vr4jput/churm-prediction"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/V41BH4VR4JPUT/Churm-Prediction","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/V41BH4VR4JPUT%2FChurm-Prediction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/V41BH4VR4JPUT%2FChurm-Prediction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/V41BH4VR4JPUT%2FChurm-Prediction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/V41BH4VR4JPUT%2FChurm-Prediction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/V41BH4VR4JPUT","download_url":"https://codeload.github.com/V41BH4VR4JPUT/Churm-Prediction/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/V41BH4VR4JPUT%2FChurm-Prediction/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262063551,"owners_count":23252767,"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":["churn-prediction","ensemble-model","logistic-regression","random-forest","streamlit","xgboost"],"created_at":"2025-06-26T12:10:56.687Z","updated_at":"2025-06-26T12:10:57.760Z","avatar_url":"https://github.com/V41BH4VR4JPUT.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Churn Prediction Dashboard 🚀\n\nA machine learning-powered dashboard for predicting customer churn. This project covers everything from **data preprocessing** to **model building**, **evaluation**, and a **Streamlit-based dashboard** for visual insights and predictions.\n\n---\n\n## 📌 Overview\n\nCustomer churn is a major issue in many industries. This project uses machine learning models to predict the likelihood of churn based on customer data. It includes preprocessing pipelines, model training (Logistic Regression, Random Forest, XGBoost), an ensemble model, and SHAP-based explainability.\n\n---\n\n## 📁 Directory Structure\n\n```\nv41bh4vr4jput-churm-prediction/\n├── README.md\n├── requirements.txt             # Dependencies\n├── app/                         # Streamlit app\n│   └── dashboard.py\n├── Data/                        # Final and raw datasets\n│   ├── Data.csv\n│   ├── hidden_data.csv\n│   └── processed_train.csv\n├── Models/                      # Trained models and encoders\n│   ├── Ensemble_model.pkl\n│   ├── label_encoders.pkl\n│   ├── LogisticRegression_churn_model.pkl\n│   ├── LogisticRegression_model.pkl\n│   ├── RandomForest_model.pkl\n│   ├── scaler.pkl\n│   └── XGBoost_model.pkl\n├── NoteBook/                    # Exploratory notebooks\n│   ├── PreProcessing.ipynb\n│   ├── Data.csv\n│   ├── hidden_data.csv\n│   └── processed_train.csv\n├── reports/                     # Model performance metrics\n│   └── metrics.csv\n└── utils/                       # Utility functions\n    ├── model_utils.py\n    ├── preprocessing.py\n    └── shap_explain.py\n```\n\n---\n\n## 🧠 ML Models Used\n\n* Logistic Regression\n* Random Forest Classifier\n* XGBoost Classifier\n* Ensemble Voting Classifier\n\nEach model is trained, validated, and saved in `.pkl` format for deployment.\n\n---\n\n## 📊 Model Performance\n\nPerformance metrics (accuracy, precision, recall, F1 score, ROC AUC) are stored in `reports/metrics.csv`. SHAP is used for explaining feature contributions.\n\n![Model Performance](images/model_metrics.png)\n![SHAP Summary Plot](images/shap_plots.png)\n\n---\n\n## 🖥️ Dashboard Features\n\n* Built using **Streamlit**\n* Upload data \n* View model predictions (churn or not churn)\n* Visualize SHAP values for model interpretability\n\n![Dashboard Screenshot](images/Dashboard.png)\n\n---\n\n## ⚙️ Setup Instructions\n\n### 🔽 Clone the repository\n\n```bash\ngit clone https://github.com/your-username/v41bh4vr4jput-churm-prediction.git\ncd v41bh4vr4jput-churm-prediction\n```\n\n### 📦 Install dependencies\n\n```bash\npip install -r requirements.txt\n```\n\n### 🚀 Launch the dashboard\n\n```bash\nstreamlit run app/dashboard.py\n```\n\nOpen in browser: `http://localhost:8501`\n\n---\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fv41bh4vr4jput%2Fchurm-prediction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fv41bh4vr4jput%2Fchurm-prediction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fv41bh4vr4jput%2Fchurm-prediction/lists"}