2025, Vol.35, No.2

Korea Real Estate Review 2023 KCI Impact Factor : 0.56

pISSN : 2092-5395 / eISSN : 2733-8339
https://journal.kci.go.kr/krer

This study aims to identify the variables predicting residential real estate auctions at the administrative district level in Seoul, South Korea, where housing anxiety has become a social issue due to high interest rates and charter fraud. The study forecasted areas of housing instability using time-series analysis and deep learning models. Data from 2017 to 2022 were used to predict figures for 2023 , and those from 2017 to 2023 were used to predict the figures for the first half of 2024. The results showed that the predictive accuracy of the model was higher for apartments than for non-apartments, largely because of the differences in sample size between them. However, predicting the distribution of auctions was more effective for non-apartment properties because there were significantly more cases of non-apartment auctions than those of apartment auctions. Moreover, economically vulnerable populations predominantly live in areas with a high concentration of non-apartment auctions, and housing instability is likely to worsen in these areas. This study’s findings provide key policy implications for preemptive measures for mitigating housing anxiety, such as preventing charter fraud, supporting affected tenants, and addressing the risks of involuntary relocation due to auctions.

This study analyzes the determinants of apartment prices and brand differences in Oncheon-dong (an upper-price area) and Allak-dong (a lower-price area), local submarkets located in Dongnae-gu, Busan, under the situation of double polarization. It also investigates the gap between regions in Seoul and the metropolitan area and provinces. The apartment sales price per 3.3㎡ was used as a dependent variable for the total number of apartment transactions in the region over the past five years, during the period of price increase and decrease starting in 2019. An individual cross-sectional multiple regression analysis for 5 years was conducted and compared using 12 independent variables reflecting structure, complex, location, and brand characteristics. The analysis revealed that five variables, including brand, were statistically significant. Regarding apartment brands, Oncheon-dong showed a positive effect on apartment prices (2019) and an early decline (2022), with no negative effect or statistical significance. On the other hand, the price of nonbranded apartments increased due to the negative effect, regardless of the period of increase or decrease. This means that even for nonbranded apartments, favorable developments such as the opening of new subways can affect apartment prices. These results can be used as a marketing appeal in the local real estate market, which has relatively low business feasibility or presale potential due to continuous population decline.

This study utilizes a hybrid model that combines generalized autoregressive conditional heteroskedasticity (GARCH) with the group method of data handling (GMDH) model to forecast returns and volatility. We focus on the Korean real estate investment trust (REIT) market and compare our hybrid model with the traditional GARCH and GMDH single models. The GARCH (1,1) model effectively captures the volatility clustering phenomenon but cannot fully reflect nonlinear patterns. In contrast, the GMDH model is stronger in handling nonlinearities; therefore, the hybrid model combining GARCH and GMDH is expected to have a higher forecasting performance. This study empirically analyzes Korean REIT market data from the listing date of each stock to the end of December 2024. The results show that our GARCH-GMDH hybrid model outperforms the GARCH and GMDH single models in forecasting returns and volatility, especially in short-term forecasting; the hybrid model can also stably capture extreme volatility and volatility clustering. Analyzing the differences in forecasting performance by market capitalization, trading volume, and time horizon of REITs reveals that REITs with larger market capitalizations and higher trading volumes had higher forecasting accuracy. Conversely, newly listed REITs had higher forecasting accuracy than long-term REITs.