거래사례 기반 기계학습 공간군집화를 이용한 서울 오피스 시장 권역 분석

Abstract

This study attempts to regionalize the Seoul office market by focusing on the investors’ perspectives. The study uses the transaction price data announced by the Ministry of Land, Infrastructure, and Transport and applies the Fuzzy C-Means algorithms, which are machine learning-based clustering techniques. The study found the following: First, as a result of comparing various algorithms, the Spatial Fuzzy C-Means algorithm performs the best clustering. Second, the three major office districts in Seoul form clusters differentiated from other areas. Third, the number of Dongs belonging to each district is smaller than the general consensus. The traditional business district (CBD) includes only parts of Jongno-Gu and Jung-Gu, the Yeouido business district (YBD) is composed of only Yeouido-Dong, and the Gangnam business district (GBD) comprises not many Dongs of Gangnam-Gu and Seocho-Gu. Fourth, by weakening the criteria, the clustering results in different spatial expansions by district. CBD has expanded to Seodaemun-Gu and Yongsan-Gu, whereas YBD has not expanded to Mapo-Gu or Yeongdeungpo. In particular, GBD expands to a considerable number of Dongs in Gangnam-Gu and Seocho-Gu. Fifth, the range of each district changes by period. When the office price increases rapidly, the range of each district is widened, and vice versa. These results show that, unlike the general perception of office districts, the CBD is expanding to Seodaemun-Gu and Yongsan-Gu. Moreover, Yeouido and nearby Mapo-Gu and Yeongdeungpo are not homogenous enough to be viewed as one district, and GBD is not linear but rectangular. Furthermore, Songpa-Gu does not form a spatially connected district with Seocho-Gu and Gangnam-Gu.