Retail-Sales-Analysis

Problem Statement

Analyze retail sales data to understand revenue trends, seasonal patterns, and product-level performance, and identify what drives revenue volatility.

Dataset

Retail sales transactional dataset sourced from Kaggle.

Key Columns

• date
• product_ID
• quantity_sold
• sales_price
• Category
• customer_id
• age
• gender
• purchase_frequency
• total_purchase_amount

The dataset contains mixed date formats, missing values, and real-world data inconsistencies.

Tools Used

• Python
• Pandas
• NumPy
• Matplotlib
• Seaborn

Project Structure

Retail-Sales-Analysis/ ├── Data/ ├── Notebooks/ ├── Images/ ├── Report.pdf ├── README.md

Steps Performed

1. Parsed mixed-format date values
2. Removed duplicate and invalid records
3. Handled missing product, quantity, and price values
4. Created revenue feature (quantity × price)
5. Performed monthly revenue and sales volume analysis
6. Identified top-performing products and categories

Key Insights

• Monthly revenue shows high volatility across time
• Sales volume remains comparatively stable month-to-month
• Revenue fluctuations are driven by seasonality and pricing, not order volume
• A small subset of products contributes disproportionately to total revenue

Visualizations

Conclusion

Revenue volatility in retail sales is primarily influenced by seasonal demand and price variation rather than changes in sales volume. Businesses can improve revenue stability through pricing optimization and category-level planning.