Retail Inventory Sales Analysis

Retailers often collect large amounts of sales and inventory data but struggle to turn it into clear decisions around stock, demand, and revenue performance.

I built an end-to-end retail analytics solution using Python, MySQL, and Power BI. With Python and Pandas, I cleaned and prepared the raw dataset, handling missing values based on their business meaning rather than blindly replacing them. The data was then analyzed in MySQL to explore revenue, units sold, inventory, discounts, categories, regions, and seasonal performance.

The final result was an interactive Power BI dashboard designed for quick business monitoring. It includes KPI cards for revenue, total stock, demand fulfillment, total products, and average discount, alongside sales by category, monthly seasonal performance, regional revenue and units sold, inventory by demand forecast, and seasonal distribution.

Key findings included a 95.72% demand fulfillment rate, balanced sales across the five product categories, and a near-even distribution of performance across the four seasons. The dashboard also provides a clear view of regional sales and inventory relationships, helping identify where demand and stock performance may require further attention.

Tools: Python (Pandas) · MySQL · Power BI · DAX