Strategic Analysis of Customer Churn in Telecommunications

Capstone project by Group 14, Section C.

Project Overview

This project analyzes customer churn in a telecommunications company to identify key churn drivers and generate practical, revenue-saving interventions.

• Total Customers Analyzed: 7,043
• Current Churn Rate: 26.5%
• Estimated Revenue at Risk: 137,000 per month
• Primary Goal: Reduce churn through targeted, data-backed retention strategies

Objective

Build a strategic churn intelligence framework that answers:

• Which customer segments are most likely to churn?
• Which service and billing patterns are linked to churn?
• What actions can reduce customer exits and protect monthly revenue?

Dataset & Files

• Primary File Used: SectionA_Group14_TeleCom - Clean_data.csv
• Repository Dataset File: clean_dataset/clean.csv
• Record Count: 7,043 customer profiles
• Target Variable: Churn (Yes / No)

Tools & Workflow

• Excel / Google Sheets: Pivot Tables, KPI calculations, interactive dashboards
• Python: Data cleaning and preprocessing
• Dashboard Layers:
  • Executive Scorecard: High-level churn KPIs and business impact
  • Operational View: Segment-level churn behavior for action planning

Key Insights & Statistics

• Dataset Size: 7,043 customer records
• Overall Churn Rate: 26.5%
• Estimated Revenue at Risk: ~$137,000/month
• Contract Type Risk: Month-to-month contracts account for 88% of total churn.
• Payment Behavior Risk: Electronic Check users contribute 57% of churn.
• Demographic Risk: Senior Citizens churn at ~2x the rate of non-senior customers.

Data Dictionary (Key Columns)

Column Name	Description	Data Type
customerID	Unique customer identifier	String
SeniorCitizen	Indicates if customer is a senior citizen (0/1)	Binary Integer
tenure	Number of months with the company	Integer
InternetService	Internet service type (DSL, Fiber optic, No)	Categorical
Contract	Contract type (Month-to-month, One year, Two year)	Categorical
PaymentMethod	Billing payment mode (e.g., Electronic check)	Categorical
MonthlyCharges	Monthly billed amount	Float
TotalCharges	Total billed amount since onboarding	Float
Churn	Customer churn status (Yes/No)	Binary Categorical

Data Cleaning Notes

• TotalCharges may require numeric type conversion during preprocessing.
• Validate blank or whitespace values before running aggregations.
• Ensure consistent category labels in PaymentMethod and Contract.
• Confirm Churn is standardized to Yes / No for dashboard filters.

Strategic Recommendations

1. Lock-In Contract Strategy

   • Offer targeted migration campaigns from month-to-month to 1-year/2-year plans.
   • Bundle loyalty discounts for high-risk, high-value churn segments.

2. Auto-Pay Incentive Program

   • Reduce Electronic Check dependency by incentivizing bank auto-pay and card auto-debit.
   • Provide limited-time cashback/discount on switching payment method.

3. Senior Citizen Retention Playbook

   • Launch priority support and simplified plan communication for senior customers.
   • Design tailored onboarding and proactive care calls during early tenure months.

4. Operational Churn Monitoring

   • Track weekly churn risk across contract type, payment method, and tenure cohorts.
   • Set intervention triggers in the Operational View dashboard for rapid response.

Dashboard Summaries

• Executive Scorecard
  • Churn rate, revenue-at-risk, segment contribution, and monthly trendlines
• Operational View
  • Drill-down by contract, payment method, demographics, and service usage

Dataset Analysis Screenshots

Business Impact

This analysis provides a decision-ready framework to reduce churn and protect recurring revenue.
By prioritizing contract conversion, payment behavior correction, and senior-customer retention, the organization can systematically lower churn and recover a significant share of the estimated $137k/month at risk.