This project analyzed customer churn for Cell2Cell, the 6th largest wireless company in the U.S. with 10 million customers. With a monthly churn rate of 4%, half of which is voluntary, the analysis aimed to identify key churn predictors and propose actionable strategies to improve customer retention and lifetime value (LTV).Problem: How do we proactively retain customers and increase revenue?

• Objective: Analyze customer behavior to identify churn predictors and propose retention strategies.
• Scope: Utilized a dataset representing 71,047 customers with 66 variables.
• Methodology: Applied logistic regression and other analytical techniques to derive actionable insights.

1. Data Analysis: Explored the dataset to understand customer demographics, usage patterns, and service history.
2. Predictive Modeling: Developed models to identify key factors contributing to customer churn.
3. Strategy Development: Formulated targeted retention strategies based on analytical findings.

• Equipment Age: Older devices correlated with a higher likelihood of churn.
• Service Tenure: Shorter service durations were associated with increased churn rates.

Usage Patterns: Variations in monthly usage influenced customer retention. Lower monthly usage increased churn likelihood

1. models.
2. Loyalty Programs: Implement rewards for long-term customers to enhance retention.
3. Usage-Based Rewards: Offer benefits to customers with consistent or increasing usage patterns.

My Contribution

• Used insights from the logistic regression model  to identify the key predictors of customer churn, including equipment age, unique subscriptions, and service tenure.
• Translated analytical findings into actionable insights by calculating the economic impact of churn predictors
•  Developed a tiered incentive plan to retain high-risk customer segments.
• Designed a customer segmentation framework, grouping customers into revenue deciles to tailor retention strategies and maximize profitability.
• Presented findings and strategies to a team of stakeholders to communicate the business impact and expected outcomes of the proposed retention plans.

Shout out to my teammates on this projects: Natalie, Tori and Shefali

Dataset: Explore the dataset used for analysis, including customer details and churn-related variables.

• Python Notebook: Access the Jupyter Notebook containing data preprocessing, analysis, and modeling.
• Project Documentation: Detailed documentation outlining the methodology, insights, and conclusions.
• Presentation Deck: View the presentation summarizing the key findings and recommendations.