• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.59-76
• /
• 2023

Since the COVID-19 era, the rise in apartment prices has been unconventional. In this uncertain real estate market, price prediction research is very important. In this paper, a model is created to predict the actual transaction price of future apartments after building a vast data set of 870,000 from 2015 to 2020 through data collection and crawling on various real estate sites and collecting as many variables as possible. This study first solved the multicollinearity problem by removing and combining variables. After that, a total of five variable selection algorithms were used to extract meaningful independent variables, such as Forward Selection, Backward Elimination, Stepwise Selection, L1 Regulation, and Principal Component Analysis(PCA). In addition, a total of four machine learning and deep learning algorithms were used for deep neural network(DNN), XGBoost, CatBoost, and Linear Regression to learn the model after hyperparameter optimization and compare predictive power between models. In the additional experiment, the experiment was conducted while changing the number of nodes and layers of the DNN to find the most appropriate number of nodes and layers. In conclusion, as a model with the best performance, the actual transaction price of apartments in 2021 was predicted and compared with the actual data in 2021. Through this, I am confident that machine learning and deep learning will help investors make the right decisions when purchasing homes in various economic situations.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.140-144
• /
• 2021

We humans try to pursue a better living environment along with the development of modern civilization. In particular, it is a reality that a lot of efforts are being made to improve food, clothing, and shelter. Among them, the concept of housing serves as a major function to improve the quality of life. However, the government's excessive tax rate regulation policy surrounding the sale of such houses is actually inducing annual or monthly rent expenses. Furthermore, it is a reality that even home sales are not being handled smoothly. In general, the cost of owning a house (apartment, etc.) can be divided into acquisition and possession. In addition, a lot of taxes are borne by long-term housing. Subsequently, due to the increase in the transfer tax rate due to the sale of houses, the disposal of property rights is not free. This serves as a limiting factor for market principles. If the tax rate for the transfer of multi-homed people is raised, it can cause a phenomenon that encourages yearly or monthly rent. This is a part where it seems necessary to reduce the transfer tax rate according to the multi-year retention period. If you hold it for 20 years after acquisition, you have paid a lot of taxes and returned your profits. For that reason, you should not impose a transfer tax for trading. The application of the tax-free principle for houses held for more than 20 years will respond to market principles in the future and will function effectively in annual or monthly rent policies.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.9
• /
• pp.6315-6324
• /
• 2015

This study analyses the effects of household finances on rental price of apartment in Seoul which play a major role in real estate policy. We estimate VAR models using time series data. Economy variables such as sales price of apartment in Seoul, consumer price index, hiring rate, real GNI and loan amount of housing mortgage, which relate to household finances and influence the rental price of apartment, are used for estimation. The main findings are as follows. In the short term, the rental price of apartment is impacted by economy variables. Specifically, Relative contributions of variation in rental price of apartment through structural shock of economy variables are most influenced by their own. However, in the long term, household variables are more influential to the rental price of apartment. These results are expected to contribute to establish housing price stabilization policies through understanding the relationship between economy variables and rental price of apartment.

• Korea Real Estate Review
• /
• v.24 no.1
• /
• pp.7-14
• /
• 2014

This study, as the temporal and spatial data for the real price apartment in Seoul from January 2006 to June 2013, empirically compared and analyzed the estimation result of apartment price using OLS by hedonic price model for the problem of space-time correlation, temporal autoregressive model (TAR) considering temporal effect, spatial autoregressive model (SAR) spatial effect and spatiotemporal autoregressive model (STAR) spatiotemporal effect. As a result, the adjusted R-square of STAR model was increased by 10% compared that of OLS model while the root mean squares error (RMSE) was decreased by 18%. Considering temporal and spatial effect, it is observed that the estimation of apartment price is more correct than the existing model. As the result of analyzing STAR model, the apartment price is affected as follows; area for apartment(-), years of apartment(-), dummy of low-rise(-), individual heating (-), city gas(-), dummy of reconstruction(+), stairs(+), size of complex(+). The results of other analysis method were the same. When estimating the price of real estate using STAR model, the government officials can improve policy efficiency and make reasonable investment based on the objective information by grasping trend of real estate market accurately.

• Land and Housing Review
• /
• v.12 no.2
• /
• pp.33-45
• /
• 2021

Due to recent changes in government policy, officetels have received attention as alternative assets, along with the uplift of office and apartment prices in Seoul. However, the current officetel price indexes use small-size samples and, thus, there is a critique on their accuracy. They rely on valuation prices which lag the market trend and do not properly reflect the volatile nature of the property market, resulting in 'smoothing'. Therefore, the purpose of this paper is to create the officetel price index using transaction data. The data, provided by the Ministry of Land, Infrastructure and Transport from 2005 to 2020, includes sales prices and rental prices - Jeonsei and monthly rent (and their combinations). This study employed a repeat sales model for sales, jeonsei, and monthly rent indexes. It also contributes to improving conversion rates (between deposit and monthly rent) as a supplementary indicator. The main findings are as follows. First, the officetel price index and jeonsei index reached 132.5P and 163.9P, respectively, in Q4 2020 (1Q 2011=100.0P). However, the rent index was approximately below 100.0. Sales prices and jeonsei continued to rise due to high demand while monthly rent was largely unchanged due to vacancy risk. Second, the increase in the officetel sales price was lower than other housing types such as apartments and villas. Third, the employed approach has seen a potential to produce more reliable officetel price indexes reflecting high volatility compared to those indexes produced by other institutions, contributing to resolving 'smoothing'. As seen in the application in Seoul, this approach can enhance accuracy and, therefore, better assist market players to understand the market trend, which is much valuable under great uncertainties such as COVID-19 environments.

• Journal of the Economic Geographical Society of Korea
• /
• v.25 no.1
• /
• pp.171-181
• /
• 2022

The real estate price index plays key roles as quantitative data in real estate market analysis. International organizations including OECD publish the real estate price indexes by country, and the Korea Real Estate Board announces metropolitan-level and municipal-level indexes. However, when the index is set on the smaller spatial unit level than metropolitan and municipal-level, problems occur: missing values. As the spatial scope is narrowed down, there are cases where there are few or no transactions depending on the unit period, which lead index calculation difficult or even impossible. This study suggests a supervised learning-based machine learning model to compensate for missing values that may occur due to no transaction in a specific range and period. The models proposed in our research verify the accuracy of predicting the existing values and missing values.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.116-124
• /
• 2016

In the past, once apartments were built by housing construction companies, their presale went smoothly. Therefore, the developer and construction companies in Korea were extremely competitive in the housing market. However, when the 1997 foreign exchange crisis and 2008 global financial crisis occurred, the quantity of unsold new housing stocks rapidly increased, which caused construction companies to experience a serious liquidity crisis. This paper aims at analyzing the influence of Liquidity on the Housing Market before and after Macroeconomic Fluctuations using VECM. The periods from September 2001 to September 2008 and from October 2008 to October 2015, which were before and after the Subprime financial crisis, were set as Models 1 and 2, respectively. The results are as follows. First, it is important to develop a long-term policy for the housing transaction market to improve household incomes. Second, due to the shortage in the supply of jeonse housing, structural changes in the housing market have appeared. Thus, it is necessary to seek political measures to minimize the impact of transitional changes on the market.

• Journal of the Economic Geographical Society of Korea
• /
• v.15 no.4
• /
• pp.585-600
• /
• 2012

The purpose of this study related to the liquidity impact of the housing market variables using vector auto-regressive model(VAR) and empirical analysis is to derive some policy implications. October 2003 until May 2012 using monthly data for liquidity variables mortgage rates, mortgage, financial liquidity, as the composite index and nation, Seoul, Gangnam, Gangbuk, the Apartment sales prices were analyzed. Granger Causality Test Results, mortgage rates and mortgage at a bargain price two regions had a strong causal relationship. Since the impulse response analysis, Geothermal difference there, but housing price housing price itself, the most significant ongoing positive (+) reactions were liquidity-related variables are mortgage loans is large and persistent positive (+), financial liquidity weakly positive (+), mortgage interest rates are negative (-), KOSPI, the negative (-) reacted. Liquidity and housing prices that the rise can be and Gangnam in Gangbuk is greater than the factor that housing investment was confirmed empirically. Government to consider the current economic situation, while maintaining low interest rates and liquidity of the market rather than the real estate industry must ensure that activities can be embedded and local enforcement policies should be differentiated according to the policy will be able to reap significant effect.

• 주택과사람들
• /
• s.168
• /
• pp.46-58
• /
• 2004

>>> 시장여건 분석 $\blacktriangleright$ 주택수급 상황 $\cdot$ 신규입주물량은 46만호로 올해보다 크게 감소하나 아파트입주물량은 32만호로 증가. 특히, 주거용 오피스텔 입주가 본격화되면서 전체적으로 공급과잉구조로 전환 $\cdot$ 가수요는 물론 실수요도 위축되면서 미분양 증가, 입주후 공가가 주요이슈로 대두 $\blacktriangleright$주택정책 여건 $\cdot$양도세,재산세 중과, 주택거래신고제, 종합부동산세 등 10.29종합대책의 후속조치가 본격화되고, 토지거래허가대상 확대 및 개발이익환수 등 2차 대책 시행가능성 상존 $\cdot$ 분양원가 공개, 후분양제 도입, 신행정수도 이전계획의 향방에 따른 불안요인도 내재 $\blacktriangleright$거시경제 전망 $\cdot$ 경기회복으로 금리가 상승세로 돌아설 경우 투자수요 위축 불가피 $\cdot$ 경제성장률이 $5\%$대로 개선되고 시중유동성도 풍부하나, 가계부실과 실업 증가로 수요증가효과는 제한적 >>> 향후 시장전망 $\cdot$ 저금리기조와 각종 개발호재에 따른 시장불안요인은 상존하나 정부의 강력한 투기억제 의지를 감안할 때 단기 조정 후 추가 하락하는 전형적인 경기후퇴국면에 진입할 전망 $\cdot$매매가격은 서울아파트가격이 크게 하락하면서 전국평균-$2\%$ 내외의 하락률을 보이고, 전세가격도 국지적 불안 가능성은 있으나 $-1\%$ 내외의 하향안정세가 이얼질 전망. 분양시장은 청약률 둔화와 미분양 증가의 침제양상이 이어지면서 주택건설실적도 각종 사업여건 악화로 50만호 안팎에 머물 것으로 예상. 지가상상률은 투기대책과 주택시장 위축으로 올해보다는 소폭 낮아지나 각종 개발 호재에 힘입어 개발예정지역을 중심으로 $3\%$ 내외의 높은 상승세가 지속될 전망

• Korean Journal of Construction Engineering and Management
• /
• v.17 no.3
• /
• pp.108-115
• /
• 2016

The price determinant for land investment depends on the internal information process and subjective decision making by management in general. Accordingly, the systematic frame to determine the feasibility of investment price to the public residential land for multi-housing development by private sector has not been proposed. The purpose of this study is to explore the frame to determine the investment price for public residential land from the perspectives of land attribute and apartment market factor. Multiple regression has been implemented to confirm the eligibility of proposed model. Research findings indicate that the land area, floor area ratio, coverage ratio, location have been identified as the total land cost determinant, and for the determinants for floor area land cost, the ratio of apartment, sale price, rent price, etc, have been identified. This research intends to provide the basis for land providers to predict the land value as a raw material in market and present the indicators for land buyers to review the price adequacy for the investment.