This project compare Megaline prepaid plans to identify which generates higher revenue using Python, statistics, and customer usage data.
- Loaded multiple datasets using pandas
- Inspected dataset structure, columns, and sample rows
- Cleaned and standardized data types
- Checked for missing values and duplicates
- Converted date columns for time-based analysis
- Calculated monthly usage per customer for calls, messages, and internet data
- Applied business billing rules to round usage values
- Merged customer usage data with plan details
- Calculated monthly revenue for each user
- Compared Surf and Ultimate customer behavior
- Analyzed average minutes, messages, data usage, and revenue
- Created visualizations to compare plan usage distributions
- Performed statistical hypothesis testing using SciPy
- Determined which prepaid plan generated higher average revenue
- Evaluated whether NY-NJ customer revenue differed from other regions
This project uses multiple telecom datasets containing customer account information, call records, text message activity, internet session usage, and plan pricing details. The analysis focuses on 500 Megaline customers using Surf and Ultimate prepaid plans during 2018.
- Surf users often exceeded plan limits, generating extra charges
- Ultimate users paid a higher fixed monthly fee with fewer overage charges
- Customer usage behavior differed significantly between plans
- Internet usage was one of the biggest revenue drivers
- Revenue distributions varied across customer groups
- Statistical testing showed meaningful differences in average revenue between plans
- Regional revenue comparisons identified differences between NY-NJ users and other regions
- Python
- Pandas
- NumPy
- Matplotlib
- Seaborn
- SciPy
- Jupyter Notebook