A Discovery System for Finding High-Value Homes
Buying a house is not only an emotional desire, but also a popular investment option. However, housing markets lack of tools and relevant systems of complete evaluation for house values. To this end, in this paper, we provide a discovery system for finding high-value homes. Unlike traditional housing price models, the proposed discovery system has taken both urban geography information and human mobility information into consideration. In this system, a suite of data mining functions have been developed to identify human mobility patterns by exploring human location traces as well as the interactions between human and Point of Interests (POIs). Given a set of candidate houses, the system can produce a ranked list of top-k high-value houses. Specifically, this demo system provides various application functions. First, it can support decision making of home buyers. Second, it can help home sellers to optimize their pricing strategies. Finally, it can help real estate developers for site selection, and thus help urban planning as well.
Y. Fu and H. Xiong, "A Discovery System for Finding High-Value Homes," Proceedings of the 15th IEEE International Conference on Data Mining Workshop (2015, Atlantic City, NJ), pp. 1612-1615, Institute of Electrical and Electronics Engineers (IEEE), Nov 2016.
The definitive version is available at https://doi.org/10.1109/ICDMW.2015.99
15th IEEE International Conference on Data Mining Workshop (2015: Nov. 14-17, Atlantic City, NJ)
Keywords and Phrases
Commerce; Decision making; Economics; Houses; Housing; Investments; Site selection; Urban growth; Application functions; Discovery systems; Housing markets; Human mobility; Investment Options; Point of interest; Pricing strategy; Traditional housing; Data mining; Location Traces; Point-of-Interests
International Standard Book Number (ISBN)
International Standard Serial Number (ISSN)
Article - Conference proceedings
© 2016 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
01 Nov 2016