What effect might the development of big data and AI have on the work of real estate professionals ? This paper focuses on the degree to which AI and machine learning may be able to correctly determine real estate prices - a task which occupies a central position in the work of real estate appraisers and brokers. Real estate price determination requires a process where real estate data of varying quality is utilized in the analysis of price formation structures. Furthermore, as the market is in a constant state of flux prices must be determined in response to changes over time. Big data and AI are terms that are commonly used in general conversation. While they do have a complementary relationship they have developed, fundamentally, as diff erent technologies. Recent developments in this area have garnered attention, with a particular focus on advances in big data, and in the context of the development of such an information base the significant improvements in the methods of analysis known as AI and machine learning indicate that such techniques will eventually be able to perform the task of real estate price determination that is currently carried out by appraisers and brokers.

This article describes frontier efforts to apply deep learning technologies, which is the greatest innovation of research on artificial intelligence and computer vision, to image data such as real estate property photos and floor plans. Specifically, attempts to detect property photos that violate regulations or were misclassified, and to extract information that can be used as new recommendation features from property photos, were mentioned. In addition, this article introduces an innovation created by providing datasets for academic communities.

This paper introduces the market price of house rent in SUUMO as an example of applications for big data utilization. The market price using average or median of house rent may not be appropriate with respect to the stabilization. This paper investigates the possibility of the market price using statistical models using linear regression or random forests to make the market price to be stabilized. This analysis uses the data of houses listed in SUUMO from August 2016 to October 2016 and the number of houses are about three million. The result shows that the market price using random forest with smoothing is the most appropriate in our case.

In residential real estate market, the agent has an incentive to steer her clients to her own listing or buyers rather than offering the best value transaction, which derives from allowing dual agency and information asymmetry among buyers, sellers and agents. We estimated commission levels and sale prices of real estate brokers by questionnaire survey, and found that seven out of ten brokers are making dual-agency deals and lowering sale prices. We couldnʼt find any effects of the number of employees, location of office and major types of contract on dual agency.