This research seeks to demonstrate how machine learning, a branch of artificial intelligence, is able to deliver more accurate pricing predictions, using the real estate market as an example. Utilizing 24,936 housing transaction records, this paper employs Extra Trees (ET), k–Nearest Neighbors (KNN), and Random Forest (RF) to predict property prices and then compares their results with those of a hedonic price model. In particular, this paper uses a feature (property age x square footage) instead of property age in order to isolate the effect of land depreciation on property prices. Our results suggest that these three algorithms markedly outperform the traditional statistical techniques in terms of explanatory power and error minimization. Machine learning is expected to play an increasing role in shaping our future. However, it may raise questions about the privacy, fairness, and job displacement issues. It is therefore important to pay close attention to the ethical implications of machine learning and ensure that the technology is used responsibly and ethically. Researchers, legislators, and industry players must work together to create appropriate standards and legislation to govern the use of machine learning.

Linear regression is a statistical tool used to model the relation between a set of housing characteristics and real estate prices. It estimates the mean value of the response variable, given levels of the predictor variables. The quantile regression approach complements the least squares by identifying how differently real estate prices respond to a change in one unit of housing characteristic at different quantiles, rather than estimating the constant regression coefficient representing the change in the response variable produced by a one-unit change in the predictor variable associated with that coefficient. It estimates the implicit price for each characteristic across the distribution of prices and allows buyers of higher-priced properties to behave differently from buyers of lower-priced properties, even if they are within one single housing estate. Thus, it provides a better explanation of the real-world phenomenon and offers a more comprehensive picture of the relationship between housing characteristics and prices.

This paper uses a probit model to evaluate a total of 1353 sets of cross-sectional development control (planning application) statistics not previously published for 3 classes of statutory residential zones in Hong Kong over a period of 24 years from 1975. As far as the selected zones are concerned, the findings refute the critical view that the Town Planning Board process in Hong Kong generates significant rent-seeking activities in favour of large developers. They also reject the official assertion that the decisions made by the Town Planning Board are independent of exogenous policy influence of government.