Mass Appraisal for Urban Land in Korea: A Hybrid Hedonic Pricing Approach

Abstract

This study proposes a hybrid hedonic model that improves the performance of mass appraisals in residential property markets. Our model is designed to directly capture the value of locations without assuming a specific functional form or the factors affecting it. The K-means clustering algorithm serves as subdividers to allocate indicators to samples according to locational similarity. The advantage of this approach is that it allows us to measure the value of a location using only its latitude and longitude. We examine the predictive accuracy of the model in an out-of-sample context based on apartment transaction data for Seoul, the largest city in Korea. Our results show that the explanatory power of the proposed model is significantly better than that of the conventional model.

Keywords: Hedonic model, Machine learning, Mass appraisal, Locational effect, K-means clustering

JEL Classification: C31, C63, O18