Skip to content

GeorgiaMath/ecommerce-sales-analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 

Repository files navigation

E-commerce Sales Analysis

This project was developed as part of my MSc in Business Mathematics at the Athens University of Economics and Business. The goal was to simulate the role of a data analytics manager in an e-commerce company and extract insights that can support strategic business decisions.

All analysis, visualizations, and modeling were implemented using Python from scratch without automated tools.

Dataset

The dataset includes customer transactions, product categories, unit prices, revenues, marketing campaigns, sales platform, customer region, age group, and gender.

These data are entirely anonymized and do not contain any personally identifiable information such as names, emails, or contact details. They are used solely for educational and analytical purposes within the context of this academic project.


📊 Key Analyses

1. Seasonal Analysis

  • Monthly and seasonal sales trend analysis
  • Visualization of revenue fluctuations over the year
  • Strategic suggestions based on seasonal performance patterns

2. Marketing Campaign Performance

  • Comparison of campaign revenue and volume ("No Campaign", "Spring Discounts", "Winter Discounts")
  • ROI calculation per campaign (revenue per sale)
  • Heatmap showing sales performance and campaign effectiveness

3. Customer-Centric Analysis

  • Revenue breakdown by age group and gender
  • Product preferences by demographic group
  • Insights on purchasing behavior across segments

4. Customer Profiling (Clustering)

  • Feature engineering with encoding and normalization
  • Clustering using K-Means, guided by Elbow and Silhouette methods
  • Visualization via t-SNE
  • Interpretation of customer profiles and marketing recommendations per segment

🛠 Technologies

  • Python: pandas, seaborn, matplotlib, scikit-learn
  • Clustering: K-Means, t-SNE
  • Modeling: Linear Regression, Random Forests
  • Visualization: line plots, bar charts, pie charts, heatmaps
  • Excel: initial data formatting and validation

🔍 Outcomes

  • Identification of seasonal and demographic sales trends
  • Insights into marketing campaign effectiveness
  • Actionable customer segmentation for targeted strategy

The project covers a full analytics workflow — from data exploration and visualization to clustering, forecasting, and decision-making support.

License

This project is licensed under the MIT License.

About

E-commerce sales project

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published