Figuring Out Which Employees May Quit
-
Updated
Sep 1, 2020 - Jupyter Notebook
Figuring Out Which Employees May Quit
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.
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.
cohort retention analysis using MySQL for online retail dataset
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.
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
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.
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.
A/B testing impact of progression system changes on player retention / interaction. Non-parametric hypothesis testing and power transformations for non-normally distributed data.
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.
BG/NBD and Gamma Gamma probabilistic models to evaluate and predict customer churn, retention, and lifetime value of an e-commerce business
Retention analysis of weekly subscription cohorts
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.
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.
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.
Investigating player retention using SQL and BigQuery
Telecom Customers Churn Prediction using machine Learning Algorithm by Mohd Arman
Add a description, image, and links to the retention-analysis topic page so that developers can more easily learn about it.
To associate your repository with the retention-analysis topic, visit your repo's landing page and select "manage topics."