Telecom Churn Analysis

Objective

The main objective of this project is to analyze customer churn in a telecom company, identify patterns, and provide insights to reduce churn and improve customer retention.

Tools Used

• Python
• Jupyter Notebook
• Pandas
• NumPy
• Matplotlib
• Seaborn
• Scikit-learn

Dataset

The dataset contains telecom customer information, including:

• Customer demographics
• Account information
• Usage patterns
• Churn status

Steps Taken

1. Data Collection & Loading* – Import dataset and check basic info.
2. Data Cleaning* – Handle missing values and encode categorical variables.
3. Exploratory Data Analysis (EDA)* – Analyze trends and visualize key features.
4. Feature Selection* – Identify important features affecting churn.
5. Modeling (Optional)* – Build predictive models to forecast churn (if required).
6. Visualization* – Create charts and graphs for insights.

Key Visualizations

• Churn distribution among customers
• Correlation heatmap of features
• Monthly charges vs. churn rate
• Tenure vs. churn rate
• Service-wise churn comparison

Key Insights

• Customers with higher monthly charges tend to churn more.
• Shorter-tenured customers are more likely to leave.
• Certain services (like streaming or tech support) impact churn rate significantly.
• Contract type (monthly vs. yearly) influences customer retention.

Conclusion

The analysis highlights critical factors affecting customer churn. Telecom companies can focus on pricing strategies, customer engagement, and service improvements to reduce churn and retain customers

[Download the cleaned dataset] https://docs.google.com/spreadsheets/d/1lkmXSH3c7vD_SqrxlGPeHsJGmGjxirB4/edit?usp=sharing&ouid=109490057503958008370&rtpof=true&sd=true

Hruthik SH - Data Analyst Enthusiast linkedin profile - https://www.linkedin.com/in/hruthik-s-hunugund-841a50329?utm_source=share&utm_campaign=share_via&utm_content=profile&utm_medium=android_app