Spatial Characteristics of CA: A Narrative into San Francisco

This study delves into the spatial characteristics of housing prices within California, with a specific focus on San Francisco. We explore various models to predict housing prices based on different feature sets, including coordinate and non-coordinate attributes. Through extensive analysis, we find that incorporating geographic coordinates significantly enhances the predictive accuracy of housing prices. Utilizing a neural network model, we achieve nearly 100% accuracy in predicting the quartile of median housing prices, underscoring the complexity and influence of location-specific features. Finally, we utilized i-SLFN algorithm for developing a precise price prediction model and describing communities characteristics.