search for


Analysis on a selection criterion of land transaction cases using K-means
Journal of the Korean Data & Information Science Society 2019;30:525-37
Published online May 31, 2019;
© 2019 Korean Data and Information Science Society.

Hong Jun Cho1 · Yu Jeong An2 · Ju Hee Lee3 · Young Min Kim4

1Korea Appraisal Board, 234Department of Statistics, Kyungpook National University
Correspondence to: Graduate student, Department of Statistics, Kyungpook National University, Daehakro, Bukgu, Daegu 41566, Korea. E-mail:
This research was supported by Kyungpook National University Development Project Research Fund, 2018. This work is based on part of Hongjun Cho’s department of survey statistics Master thesis.
Received March 23, 2019; Revised May 13, 2019; Accepted May 13, 2019.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Land price is calculated using the appraisal method, which is a legal basis, as a means of ensuring objectivity. The price is mainly calculated through the use of comparable transaction cases which are selected in a discretionary manner. However, when looking at the criteria for selecting comparative cases, the question of objective numerical criteria arises as the geographical location. To solve this problem, we applied the K-means clustering method to the actual transaction data of Daegu Metropolitan City from January 2017 to June 2018 to draw the objective criteria of real-world transaction of similar geographic location to those of land subject to pricing. In this study, first, we proposed to select the price range of the real transaction data and finally we proposed an algorithm to obtain the distance between the actual transaction data and the sample data of similar geographical location in the same cluster. We expect to present numerical criteria for selecting comparative cases using statistical methods.
Keywords : Clustering, comparative method, K-means, numerical criteria, selecting a comparison case.