Estimating the Gains from New Rail Transit Investment: A Machine Learning Tree Approach

Seungwoo Chin, Matthew E. Kahn, Hyungsik Roger Moon

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Urban rail transit investments are expensive and irreversible. As people differ with respect to their demand for trips, their value of time, and the types of real estate they live in, such projects are likely to offer heterogeneous benefits to residents of a city. Defining the opening of a major new subway in Seoul as a treatment for apartments close to the new rail stations, we contrast hedonic estimates based on multivariate hedonic methods with a machine learning (ML) approach. This ML approach yields new estimates of these heterogeneous effects. While a majority of the "treated" apartment types appreciate in value, other types decline in value. We cross-validate our estimates by studying what types of new housing units developers build in the treated areas close to the new train lines.

Original languageEnglish
JournalReal Estate Economics
DOIs
Publication statusAccepted/In press - 2018 Jan 1

Fingerprint

Rail
Machine learning
Real estate
Hedonic method
Value of time
Developer
Residents
Train

All Science Journal Classification (ASJC) codes

  • Accounting
  • Finance
  • Economics and Econometrics

Cite this

@article{f084c75e30bf46ed9e927df0bbce4e0b,
title = "Estimating the Gains from New Rail Transit Investment: A Machine Learning Tree Approach",
abstract = "Urban rail transit investments are expensive and irreversible. As people differ with respect to their demand for trips, their value of time, and the types of real estate they live in, such projects are likely to offer heterogeneous benefits to residents of a city. Defining the opening of a major new subway in Seoul as a treatment for apartments close to the new rail stations, we contrast hedonic estimates based on multivariate hedonic methods with a machine learning (ML) approach. This ML approach yields new estimates of these heterogeneous effects. While a majority of the {"}treated{"} apartment types appreciate in value, other types decline in value. We cross-validate our estimates by studying what types of new housing units developers build in the treated areas close to the new train lines.",
author = "Seungwoo Chin and Kahn, {Matthew E.} and Moon, {Hyungsik Roger}",
year = "2018",
month = "1",
day = "1",
doi = "10.1111/1540-6229.12249",
language = "English",
journal = "Real Estate Economics",
issn = "1080-8620",
publisher = "Wiley-Blackwell",

}

Estimating the Gains from New Rail Transit Investment : A Machine Learning Tree Approach. / Chin, Seungwoo; Kahn, Matthew E.; Moon, Hyungsik Roger.

In: Real Estate Economics, 01.01.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Estimating the Gains from New Rail Transit Investment

T2 - A Machine Learning Tree Approach

AU - Chin, Seungwoo

AU - Kahn, Matthew E.

AU - Moon, Hyungsik Roger

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Urban rail transit investments are expensive and irreversible. As people differ with respect to their demand for trips, their value of time, and the types of real estate they live in, such projects are likely to offer heterogeneous benefits to residents of a city. Defining the opening of a major new subway in Seoul as a treatment for apartments close to the new rail stations, we contrast hedonic estimates based on multivariate hedonic methods with a machine learning (ML) approach. This ML approach yields new estimates of these heterogeneous effects. While a majority of the "treated" apartment types appreciate in value, other types decline in value. We cross-validate our estimates by studying what types of new housing units developers build in the treated areas close to the new train lines.

AB - Urban rail transit investments are expensive and irreversible. As people differ with respect to their demand for trips, their value of time, and the types of real estate they live in, such projects are likely to offer heterogeneous benefits to residents of a city. Defining the opening of a major new subway in Seoul as a treatment for apartments close to the new rail stations, we contrast hedonic estimates based on multivariate hedonic methods with a machine learning (ML) approach. This ML approach yields new estimates of these heterogeneous effects. While a majority of the "treated" apartment types appreciate in value, other types decline in value. We cross-validate our estimates by studying what types of new housing units developers build in the treated areas close to the new train lines.

UR - http://www.scopus.com/inward/record.url?scp=85050893802&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050893802&partnerID=8YFLogxK

U2 - 10.1111/1540-6229.12249

DO - 10.1111/1540-6229.12249

M3 - Article

AN - SCOPUS:85050893802

JO - Real Estate Economics

JF - Real Estate Economics

SN - 1080-8620

ER -