Project Overview
In the ever-competitive landscape of retail, it is difficult to identify new ways to appeal to consumers. For this reason, customer segmentation analysis is useful, as it allows to understand who are the consumers and how they behave. Having this in-depth knowledge allows marketing practitioners to better customize offers and tactics to improve company revenue.
Objective
The primary objective was to utilize data analytics to create customer segments which would facilitate the creation of customer personas and the understanding of consumer behavior.
Tools, Skills, and Methodologies Employed
The project leveraged Python for EDA and data analysis. Google Colab was used for version control. The following libraries and technologies were employed:
- Data analysis → NumPy, Pandas
- Vizualizations → MatplotLib, Seaborn, Plotly
- Models & Metrics → Sklearn
Key Results
- Distinct Customer Segments Identified → Five unique clusters were uncovered, each with specific income levels, spending behaviors, and brand engagement patterns.
- Spending & Product Preferences → Observed how spending habits affect product preferences and online behavior
- Conversion Insights → High spenders prefer premium, in-shop experiences, while low incomers need stronger incentives but prefer simplified online purchasing
- Strategic Direction → Personalized marketing, targeted promotions, and optimized digital engagement can drive conversions and revenue growth
The Approach and Process
Data Collection & Preparation
Data sources