This project presents a comprehensive approach to solving inventory inefficiencies using structured SQL queries and Tableau visualizations. It helps retail businesses uncover stock imbalances, optimize replenishment strategies, and align inventory with demand cycles.
- Identify stockout and overstock patterns.
- Calculate key performance indicators like Inventory Turnover, Stockout Rate, and Reorder Points.
- Detect slow-moving products and forecasting mismatches.
- Visualize demand trends and category-wise performance across seasons.
- SQL (MySQL/PostgreSQL) — Core analytical queries.
- Tableau — Interactive dashboards and KPIs.
- Excel/CSV — Data source for transactional records.
- KPI Dashboards: Stockout Rate, Turnover Ratio, Avg Inventory Age.
- Sales Forecast Comparison: Actual vs Forecasted demand (by category/month).
- Inventory Status: Overstock vs Stockout days, inventory heatmaps.
- Product Segmentation: Fast-moving vs slow-moving items.
- Seasonality Insights: Category-level seasonal demand patterns.
- *Product P0067: Over 1,400 days overstocked with *no stockouts — signals excess holding cost.
- Clothing category: Strong seasonal spikes in November–December but under-forecasted.
- Slow movers like P0031 and P0085: High inventory age, low turnover — flagged for clearance.
- Winter season: Highest total sales across all categories — critical for seasonal stocking strategy.
- Replenish high-demand SKUs with proactive restocking.
- Adjust forecasting models for seasonal products.
- Identify clearance opportunities for slow-moving inventory.
- Align safety stock with actual stockout trends to reduce excess inventory.
- Enable automated alert systems based on KPI thresholds.
- Kumar Manas – IIT Roorkee