出版社：International Association for Computer Information Systems
摘要：In this paper, we estimate and predict the assessed prices of residential properties by applying machine learningalgorithms (Decision Trees and Artificial Neural Networks) on the house properties and crime data. Property valueshave become an increasingly common topic of conversation in today’s economy. After the financial crisis of 2007–2008 triggered by the United States housing market crash, the factors that determine housing prices have become ofeven greater interest to numerous parties, including government agencies, urban planners, developers, real estateprofessionals, finance professionals, and of course, most American homeowners. Overall housing market trends, thenumber of new home sales, and home-resales make up an important component of the U.S. economy. Consequently,data concerning these transactions is closely tracked for the purposes of determining economic activities andformulating appropriate monetary and fiscal policies. Companies such as Zillow, a leading real estate and rentalmarketplace provider, have grown in popularity as they focus on empowering consumers with data on the housingmarket. Zillow frequently releases housing market forecasts based on its database of more than 110 million U.S.homes - including homes for sale, homes for rent and homes not currently on the market, as well as “Zestimate homevalues”, “Zestimates for Rentals” and other home-related information.
关键词：Housing Market; Decision Trees; Neural Networks; and Linear Regression
