Built an end‑to‑end Python analysis for RUSH, a global athletic brand, to answer core commercial questions using three raw tables (products, retailers, sales). I cleaned and joined data in pandas, engineered metrics, and created visualizations in Matplotlib/Seaborn to surface quarterly trends and year‑over‑year comparisons. The notebook identifies top‑performing states by gender, the retailers driving unit volume by year (e.g., Foot Locker in 2021 vs. Amazon in 2020), and serviceable insights on category mix. Deliverables include a reproducible Jupyter notebook, clearly labeled charts (bar, line, box), and concise answers to business questions to support faster decision‑making by sales leadership.

Tech & tools: Python, pandas, NumPy, Matplotlib, Seaborn
Data: TABLE_PRODUCTS_885.csv, TABLE_RETAILER_885.csv, TABLE_SALES_885.csv
Highlights: Data cleaning & joins, KPI derivation, Y/Y & Q/Q trend analysis, retailer ranking, state‑level performance

Key business questions answered (examples)

Which states led sales for women’s and men’s products in 2021?

Which retailers purchased the most units in 2021 vs. 2020?

How do spend and units trend by product type and region?

What patterns emerge in price per unit across regions?

Notable findings (from the notebook)

Women’s 2021 top state: Maine ($2,176,301).

Men’s 2021 top state: Delaware ($2,334,300).

Top retailer by units: Foot Locker (2021) vs. Amazon (2020).

Your contribution

I designed the analysis from scratch: structured the problem, built a clean data model in pandas, validated joins/aggregations, and created visualizations to communicate trends and retailer performance. I wrote clear, reproducible code, documented assumptions, and packaged results so stakeholders can quickly extract insights or rerun the analysis.