TY - JOUR
T1 - Home Price Index
T2 - A Machine Learning Methodology
AU - Barr, Joseph
AU - Ellis, Eden A.
AU - Kassab, Antonio
AU - Redfearn, Christian L.
AU - Srinivasan, Narayanan Nani
AU - Voris, Kurtis B.
PY - 2017
Y1 - 2017
N2 - Estimating house prices is essential for homeowners and investors alike with both needing to
understand the value of their asset, and to understand real estate assets as part of an overall
portfolios. Commonly-used indices like the National Association of Realtors (NAR) median
home price index, or the celebrated Case-Shiller Home Price Index are reported exclusively over
a large geographic areas, i.e., a metropolitan, whereby home price dynamics are lost. In this
paper, we propose a improved method to capture price dynamics over time at the most granular
level possible a single home. Using over 16 years of home sale data, from the year 2000 to
2016, we estimate home price index for each house. Once home price dynamics is captured, its
possible to aggregate price dynamics to construct a price index over geographies of any kind,
e.g., ZIP code. This particular index relies on a so-called `gradient boosted' model, a methodology
framework relying on multiple calibration parameters and heavily dependent on sampling
techniques. We demonstrate that this approach offers several strengths compared to the commonly
reported indices, the `median sale' and `repeat sales' indices.
AB - Estimating house prices is essential for homeowners and investors alike with both needing to
understand the value of their asset, and to understand real estate assets as part of an overall
portfolios. Commonly-used indices like the National Association of Realtors (NAR) median
home price index, or the celebrated Case-Shiller Home Price Index are reported exclusively over
a large geographic areas, i.e., a metropolitan, whereby home price dynamics are lost. In this
paper, we propose a improved method to capture price dynamics over time at the most granular
level possible a single home. Using over 16 years of home sale data, from the year 2000 to
2016, we estimate home price index for each house. Once home price dynamics is captured, its
possible to aggregate price dynamics to construct a price index over geographies of any kind,
e.g., ZIP code. This particular index relies on a so-called `gradient boosted' model, a methodology
framework relying on multiple calibration parameters and heavily dependent on sampling
techniques. We demonstrate that this approach offers several strengths compared to the commonly
reported indices, the `median sale' and `repeat sales' indices.
U2 - 10.1142/S1793351X17500015
DO - 10.1142/S1793351X17500015
M3 - Article
VL - 11
SP - 111
EP - 133
JO - International Journal of Semantic Computing
JF - International Journal of Semantic Computing
SN - 1793-351X
IS - 1
ER -