📌 Project Overview

Zara, a flagship brand of Inditex Group, generates $20B+ in annual revenue with a ~53% gross margin. This project analyzes 6.4M+ retail transactions to uncover hidden margin opportunities and recommend data-backed strategies to improve profitability without raising prices or slowing design cycles.

❓ Problem Statement

Despite strong sales volume, Zara faces margin leakage through deep discounting, high return rates, and inconsistent store-level pricing discipline. Even a 1-2% improvement in Gross Margin could unlock $400M+ in additional annual profit. The goal is to identify which products, stores, customers, and discount patterns are driving or diluting profitability.

🗂️ Dataset Overview

• Total Records: 6,416,827 transactions
• Time Period: 2023–2025
• Files Used: • transactions.csv — 6.4M rows, 19 columns • customers.csv — 1.6M customer profiles • products.csv — 17,940 products • stores.csv — 35 store locations • employees.csv — 404 employees • discounts.csv — 181 discount campaigns

Key Metric: Gross Margin = Revenue − Production Cost Revenue = Unit Price × Quantity × (1 − Discount)

🛠️ Too🛠️ Tools & Technologiesls & Technologies

Python | Pandas | Matplotlib | Seaborn | Google Colab | Tableau

🔍 Key Findings

• 0% discount yields highest gross margin at $127.88 per transaction
• 50%+ discounts drop margin to just $43.41 — a 66% reduction
• Masculine category has highest GM at $125.31 vs Children at $78.17