Project Objective:
In this project I conducted Exploratory Data Analysis (EDA) on Adidas US 9.6 thousand sales records for FY 2020-21, focusing on retailer performance, regional sales distribution, and channel-specific trends. Using MySQL for data cleaning & ETL, Python for EDA, and Power BI for dashboarding, the project uncovers key insights to identify growth opportunities and optimize strategies to drive operational profitability.
Vital KPIs Tracked:
Revenue, Operating Profit, Units Sold, Operating Profit Margin %, Average Selling Price, Revenue per Unit & Operating Profit per Unit.
EDA Python Notebook Overview:
The notebook is divided into different sections for specific types of analysis:
- KPIs Performance Breakdown: Analyzed Top Retailers, Regions, Products, Seasons, and Sales methods contributing to Adidas’ overall Sales, Profitability, and Unit performance, identifying areas of strength and growth potential.
- Temporal Analysis: Examined Retailer, Product, Region and Seasonal trends across FY 2020-21 to highlight fluctuations in sales metrics, focusing on Covid-19 recovery patterns and identifying key surge and fall periods.
- Comparative Analysis: Compared Retailer, Region, and Product performance to identify unique trends and deviations, providing insights for targeted growth strategies.
- Geospatial Analysis: Identified Top N performing States and Cities by Sales, Operating profit and Units sold, highlighting geographical opportunities and underperforming areas.
- Distribution & Correlation Analysis: Explored Unit Price and Operating Profit Margin % distribution to uncover outliers and correlations, providing insights into product profitability and pricing strategies.
Tools used:
- Jupyter Notebook: for EDA and Visualizations
- MySQL Workbench: for Data Cleaning and ETL
- Microsoft Power BI Desktop: Data Modelling & Dashboard Design
- Microsoft Power BI Service: for Publishing Report
- GitHub: for Project Documentation
Skills: Python, EDA, Data Cleaning, Microsoft Power BI, Dashboards