Machine Learning and the Spatial Structure of House Prices and Housing Returns

41 Pages Posted: 15 Dec 2008

See all articles by Andrew Caplin

Andrew Caplin

New York University (NYU) - Department of Economics; National Bureau of Economic Research (NBER)

Sumit Chopra

affiliation not provided to SSRN

John V. Leahy

New York University (NYU) - Department of Economics; National Bureau of Economic Research (NBER)

Yann LeCun

New York University & Facebook AI Research

Trivikraman Thampy

New York University

Date Written: December 14, 2008

Abstract

Economists do not have reliable measures of current house values, let alone housing returns. This ignorance underlies the illiquidity of mortgage-backed securities, which in turn feeds back to deepen the sub-prime crisis. Using a massive new data tape of housing transactions in L.A., we demonstrate systematic patterns in the error associated with using the ubiquitous repeat sales methodology to understand house values. In all periods, the resulting indices under-predict sales prices of less expensive homes, and over-predict prices of more expensive homes. The recent period has produced errors that are not only unprecedentedly large in absolute value, but highly systematic: after a few years in which the indices under-predicted prices, they now significantly over-predict them. We introduce new machine learning techniques from computer science to correct for prediction errors that have geographic origins. The results are striking. Accounting for geography significantly reduces the extent of the prediction error, removes many of the systematic patterns, and results in far less deterioration in model performance in the recent period.

Keywords: House price index, sub prime crisis

JEL Classification: C81

Suggested Citation

Caplin, Andrew and Chopra, Sumit and Leahy, John V. and LeCun, Yann and Thampy, Trivikraman, Machine Learning and the Spatial Structure of House Prices and Housing Returns (December 14, 2008). Available at SSRN: https://ssrn.com/abstract=1316046 or http://dx.doi.org/10.2139/ssrn.1316046

Andrew Caplin (Contact Author)

New York University (NYU) - Department of Economics ( email )

269 Mercer Street, 7th Floor
New York, NY 10011
United States

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Sumit Chopra

affiliation not provided to SSRN ( email )

John V. Leahy

New York University (NYU) - Department of Economics ( email )

269 Mercer Street, 7th Floor
New York, NY 10011
United States
212-992-9770 (Phone)
212-995-4186 (Fax)

HOME PAGE: http://www.nyu.edu/fas/Faculty/LeahyJohn.html

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Yann LeCun

New York University & Facebook AI Research ( email )

60 Fifth Avenue
Room 516
New York, NY 10011
United States
2129983283 (Phone)

HOME PAGE: http://yann.lecun.com

Trivikraman Thampy

New York University ( email )

Bobst Library, E-resource Acquisitions
20 Cooper Square 3rd Floor
New York, NY 10003-711
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
2,285
Abstract Views
14,657
Rank
12,039
PlumX Metrics