Search

Predicting Sales Prices in Real Estate

Updated: Aug 18, 2020

Chinese and North American Markets

Predicting Sales Price in 70 Chinese Cities – Using Median Income as a Predictor

Note: The R^2 measures the predicting power of the median income on sales values. An R^2 of 1.00 means that the attribute explains 100% of the variations in sales prices, and an R^2 of 0.00 means it explains 0% of price variation.


Background Information

The real estate market is efficient when participants are fully rational. Housing price to income is an effective measure of efficiency, where constant ratios represent an efficient market, whereas fluctuating ratios imply speculation and inefficiency.


Results

Figure 4 shows that the sales prices cannot be easily predicted, and is proof of an inefficient real estate market. This exercise was replicated in North America with the same findings.


What does this mean?

Real estate developers must be very careful with real estate pricing. Given the real estate market is opaque and inefficient, real estate developers, landlords and brokers need to keep an eye out on pricing.


SquareFeet.ai’s price optimization solution allows developers to analyze real demand and adjust pricing based off how investors and buyers are behaving in real time. Rather than adjusting pricing with basic analytics, harvest the power of Machine Learning to guide you in your pricing decisions.


Source: Chen, Yan, et al. “Efficiency of Chinese Real Estate Market Based on Complexity-Entropy Binary Causal Plane Method.” Complexity, vol. 2020, 2020, pp. 1–15., doi:10.1155/2020/2791352.


Jordan Owen – CEO | info@squarefeet.ai | 438-290-1002

34 views0 comments

Recent Posts

See All