For the best viewing experience, please open this page on a desktop or laptop.
Leveraging machine learning to identify at-risk customers and implement targeted retention strategies that reduce churn from 16.8% to below 12%, saving approximately 270 customers and $236K in immediate revenue.
Model Accuracy
Decision Tree ClassifierCurrent Churn Rate
947 of 5,630 customersRevenue at Risk
Immediate intervention neededAnnual Retention Potential
With targeted strategiesWatch the complete project presentation explaining the business problem, technical approach, and strategic recommendations.
This project addresses a critical business challenge: 16.8% customer churn resulting in significant revenue loss for an e-commerce platform serving 5,630 customers.
Using advanced machine learning techniques, I developed a predictive model achieving 89.3% accuracy that identifies at-risk customers before they churn, enabling proactive intervention strategies.
Navigate through each phase of the analysis
Explore the dataset, understand the business context, and identify the key challenges
Explore DatasetDeep dive into the technical analysis, feature engineering, and model development
View AnalysisExplore the data through interactive Tableau visualizations and segmentation analysis
Open DashboardDiscover actionable recommendations and the 90-day implementation plan
View StrategyDownload presentation materials and access code repositories