Scalable ETL pipeline built with Apache PySpark to process 7,043 telecom customer records for churn analysis. PySpark version of etl-telco-churn (Pandas + MySQL).
Customer churn prediction and analytics system using SQL, Python, Random Forest, Power BI, and Streamlit.
Predicting telecom customer churn using machine learning and segmenting customers by churn risk to support targeted retention strategies
An automated preprocessing pipeline for Telco Customer Churn data, including cleaning, feature engineering, and CI with GitHub Actions.
Predicts telecom customer churn using Logistic Regression and Random Forest — full pipeline with EDA, feature engineering, and model evaluation (Python, scikit-learn)
Machine Learning training pipeline for Telco Customer Churn prediction with MLflow tracking, hyperparameter tuning, and DagsHub integration.
Machine learning project for predicting telecom customer churn using scikit-learn with data preprocessing, model training, evaluation, and a Streamlit interface.
Data cleaning of the Telco customer churn dataset in Python: missing values, dtype fixes and analysis-ready output.
End-to-End Customer Churn Prediction Pipeline using Scikit-learn, GridSearchCV, and Gradio. Automatically preprocesses Telco data, tunes Logistic Regression & Random Forest models, and deploys an interactive web app for real-time churn predictions.
End-to-end analytics pipeline (SQL → R → Tableau) for telco customer churn: KPIs, segment breakdowns, and revenue at risk.
AI-powered model drift detection, explanation, and recommendation platform built with FastAPI + Streamlit
Predicting telecom customer churn using Machine Learning (Logistic Regression, Random Forest) and Deep Learning (ANN) pipelines.
To associate your repository with the telco-churn topic, visit your repo's landing page and select "manage topics."