Gezinomi Customer Revenue Estimation & Segmentation Project

In this project, I applied a rule-based classification methodology on a real Gezinomi customer dataset to estimate potential income for customers. The analysis workflow includes:

• ▹ Cleaning and preprocessing raw data,
• ▹ Performing exploratory data analysis (EDA) to uncover trends,
• ▹ Applying rule-based classification for revenue estimation,
• ▹ Interpreting the segments to generate actionable business insights.

Through this structure, I visualized how customer value behaves across segments and drew insights useful for optimizing marketing strategies.

Project Story and Challenges

When I started this project, the Gezinomi dataset was quite raw and not ready for direct analysis. I performed comprehensive data cleaning to handle missing and outlier values and prepared the data for analysis. Defining meaningful business rules for rule-based classification and correctly segmenting customers was challenging because the segments needed to accurately reflect revenue levels.

During EDA, supporting findings with visualizations and explaining segment behavior to translate insights into actionable business decisions required careful technical considerations throughout the process. This gave me a rich experience in both the engineering and business sides of customer segmentation analysis.