• The Transactions of the Korea Information Processing Society
• /
• v.13 no.5
• /
• pp.209-216
• /
• 2024

Real estate market prices are determined by various factors, including macroeconomic variables, as well as the influence of a variety of unstructured text data such as news articles and social media. News articles are a crucial factor in predicting real estate transaction prices as they reflect the economic sentiment of the public. This study utilizes sentiment analysis on news articles to generate a News Sentiment Index score, which is then seamlessly integrated into a real estate price prediction model. To calculate the sentiment index, the content of the articles is first summarized. Then, using AI, the summaries are categorized into positive, negative, and neutral sentiments, and a total score is calculated. This score is then applied to the real estate price prediction model. The models used for real estate price prediction include the Multi-head attention LSTM model and the Vector Auto Regression model. The LSTM prediction model, without applying the News Sentiment Index (NSI), showed Root Mean Square Error (RMSE) values of 0.60, 0.872, and 1.117 for the 1-month, 2-month, and 3-month forecasts, respectively. With the NSI applied, the RMSE values were reduced to 0.40, 0.724, and 1.03 for the same forecast periods. Similarly, the VAR prediction model without the NSI showed RMSE values of 1.6484, 0.6254, and 0.9220 for the 1-month, 2-month, and 3-month forecasts, respectively, while applying the NSI led to RMSE values of 1.1315, 0.3413, and 1.6227 for these periods. These results demonstrate the effectiveness of the proposed model in predicting apartment transaction price index and its ability to forecast real estate market price fluctuations that reflect socio-economic trends.

• Journal of the Korean Geographical Society
• /
• v.49 no.6
• /
• pp.917-934
• /
• 2014

Geographically weighted regression(GWR) model has been widely used to estimate spatially heterogeneous real estate prices. The GWR model, however, has some limitations of the selection of different price determinants over space and the restricted number of observations for local estimation. Alternatively, the geographically weighted LASSO(GWL) model has been recently introduced and received a growing interest. In this paper, we attempt to explore various local price determinants for the real estate by utilizing the GWL and its applicability to forecasting the real estate price. To do this, we developed the three hedonic models of OLS, GWR, and GWL focusing on the sales price of apartments in Seoul and compared those models in terms of model fit, prediction, and multicollinearity. As a result, local models appeared to be better than the global OLS on the whole, and in particular, the GWL appeared to be more explanatory and predictable than other models. Moreover, the GWL enabled to provide spatially different sets of price determinants which no multicollinearity exists. The GWL helps select the significant sets of independent variables from a high dimensional dataset, and hence will be a useful technique for large and complex spatial big data.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.639-651
• /
• 2016

"Law on price announcement for real estate" which was revised as of Jan. 19, 2016 (will be enforced as of Sep. 1, 2016) decided the introduction of 'Price announcement system for non-residential property' for the first time. However, its introduction seems to be delayed based on two reasons. Firstly the methodology for introduction of non-property system is not definitized, despite many problems were brought up for current tax base of non-residential property. In addition, changes in tax base will place a burden on the government. In this regard, this study analyzed actual transaction price data throughout one year to analyze equity of taxation for non-residential property and to find major factor which affects on the tax base, in relation with the change of current public announcement system to actual transaction based system. And this is the first study that applied actual transaction price to non-residential property.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.228-234
• /
• 2021

Real estate market participants need to have a sense of predicting real estate prices in decision-making. Commonly used methodologies, such as regression analysis, ARIMA, and VAR, have limitations in predicting the value of an asset, which fluctuates due to unknown variables. Therefore, to mitigate the limitations, an artificial neural was is used to predict the price trend of apartments in Seoul, the hottest real estate market in South Korea. For artificial neural network learning, the learning model is designed with 12 variables, which are divided into macro and micro factors. The study was conducted in three ways: (Ed note: What is the difference between case 1 and 2? Is case 1 micro factors?)CASE1 with macro factors, CASE2 with macro factors, and CASE3 with the combination of both factors. As a result, CASE1 and CASE2 show 87.5% predictive accuracy during the two-year experiment, and CASE3 shows 95.8%. This study defines various factors affecting apartment prices in macro and microscopic terms. The study also proposes an artificial network technique in predicting the price trend of apartments and analyzes its effectiveness. Therefore, it is expected that the recently developed learning technique can be applied to the real estate industry, enabling more efficient decision-making by market participants.

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.5
• /
• pp.29-37
• /
• 2020

This study analyzed the importance of factors according to the investor's perspective through a survey of residential real estate experts using AHP and fuzzy theory. Analysis results showed that rent, profitability, traffic accessibility, commercial and infrastructure, and financial regulation are important in common. By expert group, financial and credit groups cited profitability, rent, traffic accessibility, supply and tax benefits, construction and development groups cited traffic accessibility, rent, direct access, profitability, commercial area and infrastructure, and appraisal and evaluation groups cited rent, profitability, transportation accessibility, financial regulation and supply as the most important factors. This showed that it had a preference characteristic that was associated with work. In other words, it focuses most on the financial perspective in investment characteristics, and it values convenience such as accessibility to transportation and commercial districts and infrastructure as its location characteristics. In addition, it was found that easing financial regulations in the market is important to expand investment in real estate. This study aims to help the business feasibility analysis of residential property developers and rational decision-making of general investors who are consumers, taking into account the various perspectives of the expert group.

• Land and Housing Review
• /
• v.12 no.4
• /
• pp.41-59
• /
• 2021

This study reviews theoretical considerations and past studies about real estate prices, macroeconomic variables, and real estate policies. Monthly data from January 2003 to June 2021 are used, and a VEC model, the most widely used multivariate time series analysis method, is employed for analysis. Through the model, the effects of macroeconomic variables and real estate regulatory policies on real estate prices in Seoul are analyzed. Findings are summarized as follows. First, macroeconomic variables such as money supply and interest rates do not have a significant impact on Seoul's apartment prices. Due to the high demand for housing and insufficient supply, there is a demand for buying a home regardless of macroeconomic booms or recessions. Second, tax and financial regulatory policies have an initial impact on the rise in apartment prices in Seoul, and their influence diminishes over time. Third, anti-speculation zones are expected to decrease apartment prices through the suppression of demand. However, these zones cause a rise in apartment prices. This could be understood as a lock-in effect due to the strengthening of capital gains tax. Fourth, the price ceiling did not decrease apartment prices. These findings propose that, in Seoul, where demand is high and supply is insufficient, the supply of high-quality and sufficient housing should be prioritized over various regulations such as tax regulations, financial regulations, anti-speculation zones, and price caps. Moreover, the findings provide an implication that city-specific real estate policies should be implemented for Seoul rather than regulation-oriented approaches in public policy.

• Journal of the Korea Convergence Society
• /
• v.10 no.3
• /
• pp.193-201
• /
• 2019

The public's interest regarding multi-household houses, one of the small-scale housings used as profit earning property, has been increasing. Previous studies regarding price, such as the rent and sales price of multi-household houses', however, were difficult to find. Thus, this study set forth to find out what characteristics influence the sales price of multi-household houses so as to provide further suggestions to investors' decision makings and developers' strategy establishments. The data was retrieved from multi-household sales transacted in Changwon City. Through empirical analysis, this paper found that prices were high in Euichang-gu and Seongsan-gu, and meaningful variables in terms of locations were distance from major trade areas(-), distance from main streets(-), and Corner site(+). Meaningful variables related to household characteristics were total floor area(+), Studio type(+), Southern exposure(+), Building age(-), and Full-furnished(+).

• Journal of the Korean Regional Science Association
• /
• v.38 no.4
• /
• pp.45-58
• /
• 2022

This study intends to compare the factors influencing the location of international schools on apartment sales and monthly rent prices for Songdo International School in Incheon, which has a history of more than 10 years. At the latest point, 10 years after the opening of the school, apartments in areas near international schools are divided into sales and monthly rent markets and analyzed. Songdo International City, designed as a planned city, was set as a spatial scope, and 2018-19, which is a relatively stable real estate period, was set as a temporal analysis period to avoid the overheating period of real estate after COVID-19. Considering the urban image of the "New Special Education Zone," such as the opening of Songdo Campus by private academies formed around international schools and domestic and foreign universities, the multiple regression model was applied based on the traditional Hedonic price model. As a result of the empirical analysis, first, differences in the price determinants of sales and monthly rent were confirmed. Second, the price influence of international schools was much higher than that of the variables. Third, the influence of international schools was more pronounced in the monthly rent market than in the sales market.

• Korea Real Estate Review
• /
• v.28 no.2
• /
• pp.7-20
• /
• 2018

This paper has statistically analyzed the determining factors that affect office building sale prices by focusing on strata property sales through the hedonic price function. In this study, 1,171 office building transaction cases were analyzed in Seoul from 2000 to 2017. To determine the influence of various factors on office building sale prices, independent variables included factors that represented macroeconomic characteristics, locational characteristics, physical characteristics, and deal characteristics. The analysis of the strata property sales, which is a major concern in this study, showed that strata property sales enjoyed a discount of about 1.56 million won per pyeong out of the entire sales. In terms of the discount rate, strata property sales were at a 12.6% discount compared to entire property sales, so it was found that strata property sales significantly influenced office building selling price. This is due to the fact that the owner of the strata property encounters more difficulties in distributing cost than the sole proprietor in terms of property rights and the exercise of management rights. The results of this study are expected to contribute in securing transparency in transactions and risk management strategies in the future.

• Korea Real Estate Review
• /
• v.28 no.1
• /
• pp.79-90
• /
• 2018

The purpose of this study was to estimate the pricing factors of residential lands in new cities by estimating the pricing model of residential lands. For this purpose, hedonic equations for each quantile of the conditional distribution of land prices were estimated using quantile regression methods and the sale price date of Jangyu New Town in Gimhae. In this study, a quantile regression method that models the relation between a set of explanatory variables and each quantile of land price was adopted. As a result, the differences in the effects of the characteristics by price quantile were confirmed. The number of years that elapsed after the completion of land construction is the quadratic effect in the model because its impact may give rise to a non-linear price pattern. Age appears to decrease the price until certain years after the construction, and increases the price afterward. In the estimation of the quantile regression, land age appears to have a statistically significant impact on land price at the traditional level, and the turning point appears to be shorter for the low quantiles than for the higher quantiles. The positive effects of the use of land for commercial and residential purposes were found to be the biggest. Land demand is preferred if there are more than two roads on the ground. In this case, the amount of sunshine will improve. It appears that the shape of a square wave is preferred to a free-looking land. This is because the square land is favorable for development. The variables of the land used for commercial and residential purposes have a greater impact on low-priced residential lands. This is because such lands tend to be mostly used for rental housing and have different characteristics from residential houses. Residential land prices have different characteristics depending on the price level, and it is necessary to consider this in the evaluation of the collateral value and the drafting of real estate policy.