Building real estate valuation models with comparative approach through case-based reasoning

Abstract

The purpose of this study is to propose an innovative real estate valuation approach called Quantitative Comparative Approach, which can estimate correction coefficients to overcome the shortcomings of subjective decisions of correction coefficients of traditional comparative approach. The principle is to assume that the price per unit area of real estate is the average price per unit area of the particular circle of housing supply and demand multiplied by the product of several dimensionless adjustment coefficients of factors. The single regression models of these adjustment coefficients can be built with the stepwise decomposition regression analysis. Then the adjustment coefficients of comparative cases and target case can be estimated with these single regression models, and finally the correction coefficients can be estimated by dividing the adjustment coefficients of target case by those of comparative case. The empirical samples are collected from four circles of supply and demand, and are divided into four data sets. The empirical results show that the Quantitative Comparative Approach is more accurate than the two classical Hedonic price approaches, multivariate regression analysis and neural networks.