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.

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.

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.

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.

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.

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

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

Retention analysis of weekly subscription cohorts

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.

Telecom Customers Churn Prediction using machine Learning Algorithm by Mohd Arman

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

cohort retention analysis using MySQL for online retail dataset

This repository contains Python pandas code to perform exploratory data analysis (EDA) on a dataset of users who churned and then rejoined the platform. The report includes the number of win-back users in each week, the average number of days it took for users to rejoin the platform.

Customer Analytics in R

PORTFOLIO

Cookie Cats is a hugely popular mobile puzzle game developed by Tactile Entertainment. In this project, we will look at the impact of a in-game feature change on player retention.

This repository contains SQL queries to calculate the retention rate for an application called Kolo. The queries are written in standard SQL and can be used with any database that supports SQL.The queries are well-documented and easy to follow. They can be used as a starting point for anyone who wants to calculate the retention rate for an app.

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.

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.