an empirical Aplication inreal wstate valuation
From: FLAIRS-02 Proceedings. Copyright © 2002, AAAI (www.aaai.org). All rights reserved.
Data Mining: An Empirical Application in Real Estate Valuation
Ruben D. Jaen
Florida International University
University Park, PC236
Miami, Fl 33199 jaenr@fiu.edu Abstract1
This paper presents the insights gained from applying data mining techniques, in particular neural networks for the purposes of developing an intelligent model used to predict real estate property values based on variety of factors. A dataset of over one thousand transactions in real estate properties was used. The dataset included 15 variables obtained from the multiple listing system (MLS) database and captured information on transactions taking place during a period of three years. The results from applying data mining techniques to predict real estate values are promising. Future plans and recommendations for further expanding the study are given.
Keywords: Data mining, real estate valuations, home appraisals Introduction
The factors that determine housing prices are of interest to urban planners, developers, real estate professionals, and financial executives as well as most American homeowners. According to a 1998 Federal Reserve survey
(Kennickell, et al., 2000), 66.2 percent of U.S. households are homeowners and housing investment amounts to 33 percent of household net worth. The number of new home sales as well as home resales are an important component of the U.S. economy and data concerning these transactions is closely tracked for the purpose of gauging economic activity and formulating appropriate monetary and fiscal policies. This paper examines the factors that determine housing prices in a sample of over 1000 home sales in Miami-Dade County during the period of 19992001.
Sales of homes take place in the marketplace dictated by the usual rules of supply and demand. Since this is not a perfect market, there is a great latitude for judgment in arriving at the selling price, thus the job of a
Data Mining: An Empirical Application in Real Estate Valuation
Ruben D. Jaen
Florida International University
University Park, PC236
Miami, Fl 33199 jaenr@fiu.edu Abstract1
This paper presents the insights gained from applying data mining techniques, in particular neural networks for the purposes of developing an intelligent model used to predict real estate property values based on variety of factors. A dataset of over one thousand transactions in real estate properties was used. The dataset included 15 variables obtained from the multiple listing system (MLS) database and captured information on transactions taking place during a period of three years. The results from applying data mining techniques to predict real estate values are promising. Future plans and recommendations for further expanding the study are given.
Keywords: Data mining, real estate valuations, home appraisals Introduction
The factors that determine housing prices are of interest to urban planners, developers, real estate professionals, and financial executives as well as most American homeowners. According to a 1998 Federal Reserve survey
(Kennickell, et al., 2000), 66.2 percent of U.S. households are homeowners and housing investment amounts to 33 percent of household net worth. The number of new home sales as well as home resales are an important component of the U.S. economy and data concerning these transactions is closely tracked for the purpose of gauging economic activity and formulating appropriate monetary and fiscal policies. This paper examines the factors that determine housing prices in a sample of over 1000 home sales in Miami-Dade County during the period of 19992001.
Sales of homes take place in the marketplace dictated by the usual rules of supply and demand. Since this is not a perfect market, there is a great latitude for judgment in arriving at the selling price, thus the job of a
References: Abraham, J.M. and P.H. Hendershott. 1996. “Bubbles in Metropolitan Housing Markets.” Journal of Housing Bartik, T.J. 1991. Who Benefits from State and Local Economic Development Policies? (Kalamazoo, Michigan: Gilbertson, Barry, 2001. “Appraisal or Valuation: An Art or a Science?” Real Estate Issues 26(3): 86-90. Ludvigson, S. and C. Steindel. 1999. “How Important is the Stock Market Effect on Consumption?” Federal Malpezzi, S. 1996. “Housing Prices, Externalities, and Regulation in U.S Malpezzi, S., G. H. Chun, and R. K. Green. 1998. “New Place-to-Place Housing Price Indexes for U.S. Pindyck, R. S. and D. L. Rubinfeld. 1981. Econometric Models and Economic Forecasts Poterba, J.M. 1991. “House Price Dynamics: The Role of Tax Policy and Demography.” Brookings Papers on Poterba, J.M. 2000. Rose, L.A. 1989. “Topographical Constraints and Urban Land Supply Indexes.” Journal of Urban Economics. Segal, D. and P. Srinivasan. 1985. “The Impact of Suburban Growth Restrictions on U.S Inflation, 1975-78.” Urban Geography 6(l): 14-26. Starr-McCluer, M. 1998. “Stock Market Wealth and Consumer Spending.”