Deep neural network as a tool for appraising housing prices: a case study of Busan, South Korea

S. An; Y. Song; H. Jang; K. Ahn

doi:10.1088/1742-6596/2287/1/012019

Deep neural network as a tool for appraising housing prices: a case study of Busan, South Korea

S. An, Y. Song, H. Jang, K. Ahn^*

^*Corresponding author for this work

Finance and Accounting

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

51 Downloads (Pure)

Abstract

This study examines whether the number of hidden layers in a deep neural network significantly influences the model accuracy and efficiency for appraising housing prices. We provide empirical evidence that the deep neural network can achieve high accuracy with a small number of hidden layers on our dataset, which contains various hedonic variables. Furthermore, we show that adding layers does not necessarily guarantee the model's accuracy and effectiveness of the computing time.

Original language	English
Title of host publication	ICAPM 2022Conference Proceedings
Publisher	IOP Publishing
Number of pages	5
Volume	2287
DOIs	https://doi.org/10.1088/1742-6596/2287/1/012019
Publication status	Published - 1 Jun 2022
Event	12th International Conference on Applied Physics and Mathematics - Online, Unknown Duration: 18 Feb 2022 → 20 Feb 2022 http://icapm.org/2022.html (Link to conference website)

Publication series

Name	Journal of Physics: Conference Series
Publisher	IOP Publishing
ISSN (Print)	1742-6588

Conference

Conference	12th International Conference on Applied Physics and Mathematics
Abbreviated title	ICAPM 2022
Country/Territory	Unknown
Period	18/02/22 → 20/02/22
Internet address	http://icapm.org/2022.html (Link to conference website)

Keywords

deep neural network
housing prices
South Korea

ASJC Scopus subject areas

General Physics and Astronomy

Documents and Links

10.1088/1742-6596/2287/1/012019

An, S. et al (2022) Deep neural network as a tool for appraising housing prices: a case study of Busan, South Korea
Content from this work may be used under the terms of theCreative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. Published under licence by IOP Publishing Ltd.
Final published version, 704 KBLicence: CC BY

Cite this

@inproceedings{4cb44bffb0574255a1f197455d88fa1e,

title = "Deep neural network as a tool for appraising housing prices: a case study of Busan, South Korea",

abstract = "This study examines whether the number of hidden layers in a deep neural network significantly influences the model accuracy and efficiency for appraising housing prices. We provide empirical evidence that the deep neural network can achieve high accuracy with a small number of hidden layers on our dataset, which contains various hedonic variables. Furthermore, we show that adding layers does not necessarily guarantee the model's accuracy and effectiveness of the computing time.",

keywords = "deep neural network, housing prices, South Korea",

author = "S. An and Y. Song and H. Jang and K. Ahn",

year = "2022",

month = jun,

day = "1",

doi = "10.1088/1742-6596/2287/1/012019",

language = "English",

volume = "2287",

series = "Journal of Physics: Conference Series",

publisher = "IOP Publishing",

booktitle = "ICAPM 2022Conference Proceedings",

note = "12th International Conference on Applied Physics and Mathematics, ICAPM 2022 ; Conference date: 18-02-2022 Through 20-02-2022",

url = "http://icapm.org/2022.html",

}

An, S, Song, Y, Jang, H & Ahn, K 2022, Deep neural network as a tool for appraising housing prices: a case study of Busan, South Korea. in ICAPM 2022Conference Proceedings. vol. 2287, Journal of Physics: Conference Series, IOP Publishing, 12th International Conference on Applied Physics and Mathematics, Unknown, 18/02/22. https://doi.org/10.1088/1742-6596/2287/1/012019

TY - GEN

T1 - Deep neural network as a tool for appraising housing prices: a case study of Busan, South Korea

AU - An, S.

AU - Song, Y.

AU - Jang, H.

AU - Ahn, K.

PY - 2022/6/1

Y1 - 2022/6/1

N2 - This study examines whether the number of hidden layers in a deep neural network significantly influences the model accuracy and efficiency for appraising housing prices. We provide empirical evidence that the deep neural network can achieve high accuracy with a small number of hidden layers on our dataset, which contains various hedonic variables. Furthermore, we show that adding layers does not necessarily guarantee the model's accuracy and effectiveness of the computing time.

AB - This study examines whether the number of hidden layers in a deep neural network significantly influences the model accuracy and efficiency for appraising housing prices. We provide empirical evidence that the deep neural network can achieve high accuracy with a small number of hidden layers on our dataset, which contains various hedonic variables. Furthermore, we show that adding layers does not necessarily guarantee the model's accuracy and effectiveness of the computing time.

KW - deep neural network

KW - housing prices

KW - South Korea

U2 - 10.1088/1742-6596/2287/1/012019

DO - 10.1088/1742-6596/2287/1/012019

M3 - Conference contribution

VL - 2287

T3 - Journal of Physics: Conference Series

BT - ICAPM 2022Conference Proceedings

PB - IOP Publishing

T2 - 12th International Conference on Applied Physics and Mathematics

Y2 - 18 February 2022 through 20 February 2022

ER -

Deep neural network as a tool for appraising housing prices: a case study of Busan, South Korea

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Documents and Links

Fingerprint

Cite this