{"id":49592764,"url":"https://github.com/ceodaniyal/telecom_customer_churn_prediction","last_synced_at":"2026-05-04T01:40:12.822Z","repository":{"id":337295876,"uuid":"1153020683","full_name":"ceodaniyal/telecom_customer_churn_prediction","owner":"ceodaniyal","description":"A machine learning project that predicts whether a telecom customer will churn (leave the service) using customer demographics, account information, and service usage. The repository includes data preprocessing, model training (with logistic regression), feature scaling, and example predictions.","archived":false,"fork":false,"pushed_at":"2026-02-09T06:36:21.000Z","size":816,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-04T01:39:47.188Z","etag":null,"topics":["classification","customer-churn-prediction","data-science","logistic-regression","machine-learning","ml-project","pandas","prediction","python","scikit-learn","streamlit","telecom"],"latest_commit_sha":null,"homepage":"https://telecomcustomerchurnprediction-4ihq7aesvxe8dxfknyzysm.streamlit.app/","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/ceodaniyal.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-08T19:27:46.000Z","updated_at":"2026-02-09T09:24:09.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ceodaniyal/telecom_customer_churn_prediction","commit_stats":null,"previous_names":["ceodaniyal/telecom_customer_churn_prediction"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ceodaniyal/telecom_customer_churn_prediction","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceodaniyal%2Ftelecom_customer_churn_prediction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceodaniyal%2Ftelecom_customer_churn_prediction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceodaniyal%2Ftelecom_customer_churn_prediction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceodaniyal%2Ftelecom_customer_churn_prediction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ceodaniyal","download_url":"https://codeload.github.com/ceodaniyal/telecom_customer_churn_prediction/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceodaniyal%2Ftelecom_customer_churn_prediction/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32591603,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T22:12:39.696Z","status":"ssl_error","status_checked_at":"2026-05-03T22:09:10.534Z","response_time":103,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["classification","customer-churn-prediction","data-science","logistic-regression","machine-learning","ml-project","pandas","prediction","python","scikit-learn","streamlit","telecom"],"created_at":"2026-05-04T01:40:11.417Z","updated_at":"2026-05-04T01:40:12.788Z","avatar_url":"https://github.com/ceodaniyal.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 📞 Telecom Customer Churn Prediction\r\n\r\nA machine learning project to predict customer churn for a telecom company using historical usage and demographic data. By analyzing customer attributes and behavior, this project builds a predictive model that identifies customers likely to leave (churn), helping businesses improve retention strategies and reduce revenue loss.\r\n\r\n---\r\n\r\n## 📌 Table of Contents\r\n\r\n* 🔍 [Problem Statement](#-problem-statement)\r\n* 🎯 [Objective](#-objective)\r\n* 📦 [Dataset](#-dataset)\r\n* 🛠️ [Tech Stack](#-tech-stack)\r\n* 🧠 [Methodology](#-methodology)\r\n* 📈 [Model Training \u0026 Evaluation](#-model-training--evaluation)\r\n* 🚀 [Usage](#-usage)\r\n* 🧾 [Project Structure](#-project-structure)\r\n* 📊 [Results \u0026 Insights](#-results--insights)\r\n* 📌 [Future Work](#-future-work)\r\n* 📍 [Contact](#-contact)\r\n\r\n---\r\n\r\n## 🔍 Problem Statement\r\n\r\nTelecom companies face a major challenge: **customer churn** — when existing customers discontinue services for a competitor. As acquiring new customers is significantly more expensive than retaining existing ones, predicting churn to proactively retain high-risk customers is critical for profitability and strategic decision-making.\r\n\r\n---\r\n\r\n## 🎯 Objective\r\n\r\nBuild a robust machine learning model that:\r\n\r\n* Predicts whether a customer will churn or not.\r\n* Identifies key factors contributing to churn.\r\n* Supports data-driven customer retention strategies.\r\n\r\n---\r\n\r\n## 📦 Dataset\r\n\r\nThe project uses the `Telco_Customer_Churn.csv` dataset, containing customer information such as:\r\n\r\n* Customer demographics (gender, senior citizen status, dependents)\r\n* Account details (tenure, contract type, billing method)\r\n* Service subscriptions (internet, tech support, online security)\r\n* Financial details (monthly charges, total charges)\r\n* Target variable: `Churn` (Yes/No)\r\n\r\n---\r\n\r\n## 🛠️ Tech Stack\r\n\r\nThis project utilizes:\r\n\r\n* 🐍 **Python**\r\n* 📊 **pandas**, **NumPy**\r\n* 📉 **matplotlib**, **seaborn**\r\n* 🤖 **scikit-learn** for ML modeling\r\n* 🔄 **joblib / pickle** for model persistence\r\n* 🧠 Jupyter Notebook for experimentation\r\n\r\n---\r\n\r\n## 🧠 Methodology\r\n\r\n1. **Data Cleaning \u0026 Preprocessing**\r\n\r\n   * Handle missing values\r\n   * Encode categorical features\r\n   * Scale/Normalize numerical features using `MinMaxScaler` (saved as `minmax_scaler.joblib`)\r\n\r\n2. **Exploratory Data Analysis (EDA)**\r\n\r\n   * Understand customer distribution by churn\r\n   * Analyze patterns across features like contract type and monthly charges\r\n\r\n3. **Model Training**\r\n\r\n   * Train classification models\r\n   * Start with baseline models like Logistic Regression\r\n   * Save best model (`logistic_regression.pkl`)\r\n\r\n4. **Evaluation**\r\n\r\n   * Accuracy, Precision, Recall\r\n   * Confusion matrix and other metrics\r\n\r\n---\r\n\r\n## 📈 Model Training \u0026 Evaluation\r\n\r\nThe Logistic Regression model is trained to classify customers as either:\r\n\r\n* **Churn = Yes**\r\n* **Churn = No**\r\n\r\nThe trained model and preprocessor are stored as:\r\n\r\n* `logistic_regression.pkl` — Trained ML model\r\n* `minmax_scaler.joblib` — Preprocessing scaler\r\n\r\nYou can evaluate performance on a hold-out test set or cross-validation.\r\n\r\n---\r\n\r\n## 🚀 Usage\r\n\r\n### 💻 Run the Prediction Script\r\n\r\n1. Clone the repository:\r\n\r\n   ```bash\r\n   git clone https://github.com/ceodaniyal/telecom_customer_churn_prediction.git\r\n   cd telecom_customer_churn_prediction\r\n   ```\r\n\r\n2. Install dependencies:\r\n\r\n   ```bash\r\n   pip install -r requirements.txt\r\n   ```\r\n\r\n3. Run the prediction script:\r\n\r\n   ```bash\r\n   python main.py\r\n   ```\r\n\r\n### 📊 Prediction\r\n\r\nProvide customer feature values via the script interface or API endpoint (if integrated) to get churn predictions.\r\n\r\n---\r\n\r\n## 🧾 Project Structure\r\n\r\n```\r\ntelecom_customer_churn_prediction/\r\n├── Telco_Customer_Churn.csv        # Churn dataset\r\n├── telecom_customer_churn_prediction.ipynb  # Notebook with EDA \u0026 modeling\r\n├── main.py                         # Inference script\r\n├── logistic_regression.pkl         # Saved trained model\r\n├── minmax_scaler.joblib            # Preprocessing scaler\r\n├── pyproject.toml                  # Project metadata / dependencies\r\n├── .gitignore\r\n└── README.md\r\n```\r\n\r\n---\r\n\r\n## 📊 Results \u0026 Insights\r\n\r\nTypical insights from this kind of churn prediction (can be updated with your actual results):\r\n\r\n* 📈 **Monthly charges**, **Contract type**, and **Tenure** often strongly correlate with churn likelihood.\r\n* 🧑‍🤝‍🧑 Customers with **month-to-month contracts churn more** than those on long-term plans. ([GitHub][1])\r\n* 📉 **Paperless billing customers** tend to show higher churn rates. ([GitHub][1])\r\n\r\n---\r\n\r\n## 📌 Future Work\r\n\r\nFuture improvements could include:\r\n\r\n* Feature engineering (interaction terms, tenure buckets, etc.)\r\n* Hyperparameter tuning (GridSearch / RandomSearch)\r\n* Ensemble methods like Random Forest / Gradient Boosting\r\n* Handling class imbalance (SMOTE)\r\n* Deployment (Flask/Streamlit app)\r\n\r\n---\r\n\r\n## 📍 Contact\r\n\r\nHave questions or feedback? Reach out:\r\n\r\n📧 **Email:** [kdaniyal7865@gmail.com](mailto:kdaniyal7865@gmail.com)\r\n\r\n\r\n[1]: https://github.com/Pradnya1208/Telecom-Customer-Churn-prediction?utm_source=chatgpt.com \"GitHub - Pradnya1208/Telecom-Customer-Churn-prediction: Customers in the telecom industry can choose from a variety of service providers and actively switch from one to the next. With the help of ML classification algorithms, we are going to predict the Churn.\"\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fceodaniyal%2Ftelecom_customer_churn_prediction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fceodaniyal%2Ftelecom_customer_churn_prediction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fceodaniyal%2Ftelecom_customer_churn_prediction/lists"}