Measuring land lot shapes for property valuation
| Date | 08 August 2023 |
| Pages | 267-279 |
| DOI | https://doi.org/10.1108/DTA-12-2022-0461 |
| Published date | 08 August 2023 |
| Author | Changro Lee |
Measuring land lot shapes for
property valuation
Changro Lee
Kangwon National University, Chuncheon, Republic of Korea
Abstract
Purpose –Unstructured data such as images have defied usage in property valuation for a long time.
Instead, structured data in tabular format are commonly employed to estimate property prices. This study
attempts to quantify the shape of land lots and uses the resultant output as an input variable for subsequent
land valuation models.
Design/methodology/approach –Imagery data containing land lot shapes are fed into a convolutional
neural network, and the shape of land lots is classified into two categories, regular and irregular-shaped.
Then, the intermediate output (regularity score) is utilized in four downstream models to estimate land
prices: random forest, gradient boosting, support vector machine and regression models.
Findings –Quantification of the land lot shapes and their exploitation in valuation led to an improvement in
the predictive accuracy for all subsequent models.
Originality/value –The study findings are expected to promote the adoption of elusive price determinants
such as the shape of a land lot, appearance of a house and the landscape of a neighborhood in property
appraisal practices.
Keywords Land lot shape, Imagery data, Neural network, Unstructured data, Property valuation, Land
price
Paper type Research paper
1. Introduction
The real estate industry is witnessing a drastic digital transformation, and the term
PropTech [1] succinctly represents this market trend. PropTech has been rigorously
applied in various real estate industries, including building information modeling, asset
management and property brokerage and for the approval of collateral loans. The most
active area of application is property valuation (Niu and Niu, 2019). Employing artificial
intelligence technology, the property valuation industry collects diverse variables and feeds
them into advanced valuation models such as random forest (RF), gradient boosting (GB)
and neural networks. This valuation approach contributes to increasing the productivity
and competitiveness of the valuation industry.
However, the input data used for valuation have been limited to traditional structured data,
that is, data organized to reside in a database with rows and columns (Ryan, 2020). It is
convenient to process structured data using numerical models. The most common input data
for house valuation include the number of rooms, floor area and year of build (Endel et al., 2020),
all of which are categorized as structured data. In contrast, unstructured data such as images
and free-form texts are difficult-to-process variables that cannot be directly utilized in valuation.
Therefore, in case it were imperative to use such hard-to-measure variables in valuation, like the
aesthetics of a neighborhood and quality of house exteriors, a relevant formula was created
manually by domain experts, and the rule was then applied to the task at hand. However, this
rule-based approach does not always perform satisfactorily in many cases.
As the use ofmachine learning techniquesspreads widely, thesehard-to-measure variables
are now being used in valuation differently, compared to the rule-based approach. Machine
learning techniques are renowned for theirability to process unstructured dataefficien tly. In
this study, we applied a machine learning approach to quantify unstructured data.
ThecurrentissueandfulltextarchiveofthisjournalisavailableonEmeraldInsightat:
https://www.emerald.com/insight/2514-9288.htm
267
Received 8 December 2022
Revised 31 March 2023
7 July 2023
14 July 2023
Accepted 25 July 2023
Data Technologies and
Applications
Vol. 58 No. 2, 2024
pp. 267-279
© Emerald Publishing Limited
2514-9288
DOI 10.1108/DTA-12-2022-0461
Measuring
land lot shapes
Get this document and AI-powered insights with a free trial of vLex and Vincent AI
Get Started for FreeStart Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting