South Carolina Real Estate Dataset 2025
Dataset Overview
This comprehensive real estate dataset contains over 5,000 property listings from South Carolina, collected in 2025 from Realtor.com using apify api. The dataset captures diverse property types including single-family homes, condominiums, land parcels, townhomes, and other residential properties. This dataset provides a rich snapshot of South Carolina's real estate market suitable for predictive modeling, market analysis, and investment research.
Data Science Applications
- Price Prediction Models: Build regression models (Random Forest, XGBoost, Neural Networks) to predict property values based on size, location, bedrooms, and age
- Property Type Classification: Develop multi-class classifiers to categorize properties based on physical characteristics
- Market Segmentation: Apply clustering algorithms (K-means, DBSCAN) to identify distinct property segments and price brackets
- Time Series Analysis: Analyze construction trends and property age distributions to forecast future development patterns
- Investment Opportunity Detection: Create anomaly detection models to identify undervalued properties or outliers
- Feature Engineering: Generate derived features like price per square foot, bathroom-to-bedroom ratios for enhanced model performance
Column Descriptors
- type: Primary property category (single_family, condos, land, townhomes, multi_family, farm)
- sub_type: Detailed property classification (condo, townhouse, co_op)
- sqft: Property size in square feet
- baths: Number of bathrooms (decimal values indicate half baths)
- beds: Number of bedrooms
- stories: Number of floors/stories in the property
- year_built: Construction year of the property
- listPrice: Property listing price in USD
Ethically Obtained Data
This dataset was ethically scraped from publicly available listings on Realtor.com and is provided strictly for educational and learning purposes only. The data collection complied with ethical web scraping practices and contains only publicly accessible information. Users should utilize this dataset exclusively for academic research, educational projects, and learning data science techniques. Any commercial use is strictly prohibited.