warehouse dataset

📘 Instructions for Use of Dataset and Analysis Tools

This dataset, titled Warehouse Capacity and Spatial Logistics Dataset ($\mathcal{W}_{\text{data}}$), provides a synthetic yet realistic representation of warehouse infrastructure and operational capacity across multiple spatial coordinates. It is designed to support research and development in the areas of warehouse logistics optimization, capacity utilization, supply chain management, spatial analytics, and intelligent resource allocation.

🔧 Dataset Contents

• Format: CSV
• Size: 4,132 records × 11 attributes
• Source: Synthesized using Gretel.ai based on structure referenced from TI Supply Chain API – Storage Locations

📊 Suggested Tasks for Competitions and Research

Researchers and participants are encouraged to utilize the dataset for a wide variety of data-driven logistics and AI challenges, including but not limited to:

1. Clustering & Classification
   • Segment warehouses by capacity status, geography, or utilization patterns
   • Predict Capacity Status using spatial and operational variables
2. Outlier Detection
   • Identify anomalous facilities based on unusual capacity usage or spatial isolation
3. Optimization Algorithms
   • Develop algorithms for optimizing storage distribution and facility deployment
4. Geospatial Analysis
   • Explore spatial clustering or coverage using X and Y coordinates
5. Feature Importance & Ranking
   • Compute feature relevance for warehouse classification or ranking

🛠️ Recommended Analysis Tools

• Python Libraries:
  • pandas, numpy – Data manipulation
  • matplotlib, seaborn, plotly – Visualization
  • scikit-learn – ML modeling and clustering
  • xgboost, lightgbm – Advanced classification/regression
  • geopandas, folium – Optional geospatial mapping
• Notebooks/Environments:
  • Jupyter Notebook
  • Google Colab
  • VSCode + Python

• 📥 Getting Started

• Download the CSV file and load it using Python (e.g., pd.read_csv("warehouse_dataset.csv"))
• Check for structure & preview: df.head(), df.info()
• Perform preprocessing if needed (note: the dataset is already clean and balanced)
• Select a challenge such as classification, prediction, clustering, or logistics optimization
• Document your methodology and results for reproducibility

✅ Licensing and Ethics

This dataset is synthetic and does not contain personal or sensitive data. It is shared under a CC BY 4.0 license, and you are free to use it for academic, educational, and research purposes with appropriate citation.