Unlock actionable insights and boost customer retention with this Power BI project. Analyze and visualize risk factors to proactively prevent churn. ➡️

Customer churn prediction with Python using synthetic datasets. Includes data generation, feature engineering, and training with Logistic Regression, Random Forest, and Gradient Boosting. Improved pipeline applies hyperparameter tuning and threshold optimization to boost recall. Outputs metrics, reports, and charts.

Comprehensive Power BI dashboards showcasing insights on Call Centre Trends, Customer Retention, and Diversity & Inclusion to drive business impact.

Analysis and Prediction of the Customer Churn Using Machine Learning Models (Highest Accuracy) and Plotly Library

Machine Learning, EDA, Classification tasks, Regression tasks for customer churn

Telco Churn Analysis and Modeling is a comprehensive project focused on understanding and predicting customer churn in the telecommunications industry. Utilizing advanced data analysis and machine learning techniques, this project aims to provide insights into customer behavior and help develop effective strategies for customer

Analyze your customer database with ease

In this BI consultancy project, I advised the CMO of Maven Communications on how to reduce customer churn, using data.

📊 A machine learning project to predict customer churn using classification models like Random Forest, Decision Tree, and XGBoost. Includes data preprocessing, SMOTE for class balancing, hyperparameter tuning, and model deployment using pickle.

📂 Task's and work completed during my internship at Saiket_System, focusing on Data Science.🧑‍💻

Utilizing tools such as Spark, Python (PySpark), SQL, and Databricks, performed logistic regression on customers to predict those at a higher risk of churning, then applied the model to an unseen "new customers" data set.

An end-to-end machine learning project predicting bank customer churn with a Gradient Boosting Classifier. It features a complete pipeline for data processing, model training, and real-time predictions via a Flask API. SMOTE is used for handling imbalanced data, and MLflow is integrated for model tracking.

This is a Machine Learning + Flask Web App that predicts whether a customer is likely to churn and suggests a discount policy based on churn probability.

Telecom Customer segmentation and Churn Prediction

Proyecto de Ciencia de Datos para predecir la fuga de clientes. Implementa un enfoque avanzado con Variables Fantasma (Ghost Variables) para la selección de características y un modelo Random Forest para la clasificación.

Churn prediction has become a very important part of Syriatel's company strategy. This project uses machine learning algorithms to build a model that can accurately predicts customers who are likely to churn.

Machine learning project to predict customer churn using end-to-end data preprocessing, feature engineering, model training, evaluation, and deployment-ready artifacts.

End-to-end Telecom Customer Churn Analysis using PostgreSQL, Python EDA, and Machine Learning (Logistic Regression & Random Forest).

The project predicts bank customer churn using an Artificial Neural Network (ANN). It includes data preprocessing, model training with TensorFlow and Keras, and deployment via a Streamlit app. The model's performance is visualized using TensorBoard, showcasing effective machine learning techniques for customer retention.

A data-driven predictive model to identify SME customers at risk of churning, enabling targeted retention strategies for PowerCo.