Submarket, Heterogeneity and Hedonic Prediction Accuracy of Real Estate Prices: Evidence from Shanghai

This paper contributes to the literature by examining how much the prediction accuracy of real estate prices could be improved by applying hedonic equations at suitably defined disaggregate levels and incorporating directional heterogeneity of distance gradients. We build our empirical analysis on a large-scale database of real estate projects sold between 2005 and 2007 in Shanghai. Our analysis suggests that the Shanghai real estate market is a complex aggregate and taking into account submarket and directional heterogeneity in hedonic regressions could provide considerable benefits in improving the precision of real estate price predictions.