Telecom Customer Churn Analysis & Prediction project uses Gradient Boosting for precise predictions, Power BI for churn pattern visualizations, and Streamlit for interactive insights. With robust code and meticulous data preprocessing, stakeholders access accurate predictions to optimize retention and drive profitability.

BG/NBD and Gamma Gamma probabilistic models to evaluate and predict customer churn, retention, and lifetime value of an e-commerce business

A predictive model for player retention/churn on day-14 after game installation based on features such as in-game metrics, user behavior, and engagement patterns to identify players at risk of churning, accurately predicting 65% of all retention within the top 6% of total population.

Investigating player retention using SQL and BigQuery

cohort retention analysis using MySQL for online retail dataset

Extract data from Excel report to convert to a Power BI data model using industry best practices to create a demo replacement customer retention report.

The Bank Customer Churn Model is a predictive analytics solution using a high-accuracy Random Forest model to identify high-risk customers, enabling banks to proactively retain valuable customers, minimize revenue loss, and inform targeted retention initiatives through user-friendly streamlit web application. User can access churn risk probability.

Built a customer segmentation model for SBI Life Insurance using K-Means, Hierarchical, and DBSCAN clustering, applying data preprocessing and evaluation techniques to provide tailored product recommendations and boost revenue.

Telecom Customers Churn Prediction using machine Learning Algorithm by Mohd Arman

RFM is a customer segmentation model that identifies high-value customers based on their behavior. Machine learning can be used to analyze large datasets and develop predictive models to identify customers likely to become high-value. This enables businesses to target these customers with personalized marketing strategies for increased revenue.

Figuring Out Which Employees May Quit

PORTFOLIO

This is a simple project that aims to create a basic Artificial Neural Network to predict if bank customers are going to maintain/close their accounts.

A/B testing impact of progression system changes on player retention / interaction. Non-parametric hypothesis testing and power transformations for non-normally distributed data.

In this project, we conduct a time-based cohort and retention analysis in python to examine how many customers are staying and how many are leaving in a given cohort over time.

Predicted rider retention for a taxi service and identified most significant factors that contributed to it. Achieved an 80% accuracy with a catboost model, which was chosen for its interpretability.

This is working with SQL queries from the book SQL FOR DATA ANALYSIS by Cathy Tanimura

Retention analysis of weekly subscription cohorts

An comprehensive data analysis of a particular market and its customers.