Abstract
| Original language | English |
|---|---|
| Pages (from-to) | 111-133 |
| Number of pages | 23 |
| Journal | International Journal of Semantic Computing |
| Volume | 11 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 2017 |
Fingerprint
Cite this
}
Home Price Index : A Machine Learning Methodology. / Barr, Joseph; Ellis, Eden A. ; Kassab, Antonio ; Redfearn, Christian L. ; Srinivasan, Narayanan Nani ; Voris, Kurtis B. .
In: International Journal of Semantic Computing, Vol. 11, No. 1, 2017, p. 111-133.Research output: Contribution to journal › Article › Research › peer-review
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 -