Case Study: Analyzing Customer Churn for DataBel Telecom Using Power BI

Introduction:

DataBel, a leading telecom provider, engaged in a comprehensive analysis of customer churn to enhance retention strategies. Leveraging Power BI, I conducted an in-depth investigation into churn dynamics and contributing factors.

Approach:

1. Calculation of Churn Rate and Investigation Parameters: Utilized Power BI to compute churn rate and define investigation parameters through the creation of new measures and columns.

2. Churn Reasons and Categories Analysis: Investigated churn reasons sourced from customer questionnaires, categorizing them to discern prevalent issues prompting attrition.

   

3. Geographical Analysis: Identified regions with the highest churn rates and showcased regional discrepancies using conditional formatting for impactful visualization.

   

4. Demographics Examination: Analyzed churn patterns across age groups and genders to uncover demographic influences on attrition rates.

   

5. Contract and Usage Analysis: Explored contract types (yearly vs. monthly), data usage patterns, international plan adoption, contract length, and payment methods to ascertain their impact on churn.

   
   
   

6. Key Influencers Analysis: Employed Power BI's Key Influencers visualization to identify factors contributing to the increase in churn rate, facilitating targeted intervention strategies.

   

Findings:

1. Overall Churn Rate
   Through DAX measures I calculated an overall churn rate of roughly 27 percent, establishing a baseline for deeper investigation .
2. Churn Reasons & Categories
   Pricing Issues and Service Quality emerged as the two most frequently cited reasons on the post-exit questionnaire.
3. Geographical Hotspots
   A map highlighted the eastern US region as having the highest total churn, while California was the state with the highest churn rate as a single hotspot.
4. Demographic Drivers
   Senior customers (over 60 years old) churned at the highest rate (38,46 percent).
   Gender effects were modest, with males showing a marginally higher churn (+2 percent).
5. Plan & Usage Factors
   Monthly contracts experienced a significantly higher churn versus annual plans.
   High data-usage plans actually showed lower churn, suggesting “sticky” heavy users, whereas customers without any data add-on churned most.
   International calling plans and international calling activity correlated with 30 percent lower churn, indicating that roaming/calling benefits boost loyalty.
6. Key Influencers
   Power BI's Key Influencers visual flagged the strongest predictors of churn:
   • Contract category is monthly
   • Extra international charges
   • Customer is in the senior age group

Skills and Tools Utilized:

• Proficiency in Power BI: Leveraged Power BI's capabilities for data manipulation, visualization, and analysis.
• Data Analysis: Created new measures and columns for churn rate calculation and investigation parameter definition.
• Visualization Techniques: Utilized conditional formatting, different chart types, and Key Influencers analysis for insightful representation of churn dynamics.
• Interpretation and Communication: Translated analytical findings into actionable insights for strategic decision-making.

Conclusion:

Through meticulous analysis using Power BI, DataBel gained comprehensive insights into customer churn dynamics and influencing factors. Armed with these insights, DataBel can devise tailored retention strategies to mitigate churn, foster customer loyalty, and drive sustainable growth in the competitive telecom landscape. This case study underscores the importance of data-driven decision-making facilitated by advanced analytics tools like Power BI.