• Korean Journal of Construction Engineering and Management
• /
• v.16 no.1
• /
• pp.74-81
• /
• 2015

As one of urban infrastructure system, the electricity substation is critical for urban life and industrial activity as the electricity demands get higher than ever. However the substation is generally regarded as unpleasant or dangerous facility, which finally results in the continuous opposition movement by resident due to the belief of unidentified negative effect in apartment prices. Accordingly, as the scientifically objective and quantitative analysis is required to solve the social conflict, this study intends to examine the variation affected by urban infrastructure system, expecially for substation. After the independent variable defining the price of apartment and the dependent variable, which is apartment price, are identified and their spatial data has been filed, the forecasting model has been developed through the hedonic price function as well as artificial neural networks system. The research finding indicated that the spatial range affected by substation is not notable and the range of some case was applicable for less than 600m. It is expected that these research findings can be applied for establishing the one of solid cases for the analysis of economical effect to local housing market by the urban infrastructure system.

• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.11
• /
• pp.474-482
• /
• 2016

This paper presents an empirical analysis on the relationship between consumer sentiment and macro-economic indices by consumer's characteristics such as age, income and employment type. According to the empirical analysis based on the Consumer Sentiment Index(CSI) of the Bank of Korea and other macro-economic indices, the following study findings are presented. First, individual consumer sentiment depends not only on GDP growth, but also on other macro-economic conditions such as wage, employment, consumer and asset price, and debt burden. Second, the degree of importance of the macro-economic indices on determining individual consumer sentiment varies strongly according to consumers' characteristics. These findings reveal that the gap between consumer sentiment and GDP growth can largely be explained by considering the other macro-economic indices and consumer's characteristics.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.5
• /
• pp.1147-1154
• /
• 2016

Impact of Korea train express (KTX) on the regional economy in Korea has been studied by many researchers. Current research is limited in the lack of quantitative research using a statistical model to study the effect of KTX on regional economy. This paper analyses the influence of KTX to the household final consumption expenditure, which is one of important regional economic index, using spatial panel regression model. The spatial structure is introduced through spatial autocorrelation matrix using adjacency of KTX connection. The result shows a significant effect of Korea train express on the regional economy.

• Journal of Digital Convergence
• /
• v.18 no.2
• /
• pp.197-204
• /
• 2020

The purpose of this paper is to find the direction by analyzing the synchronization phenomenon and the change rate of apartment charter rate in Korea, Seoul, Busan, Daegu, Gwangju and Daejeon. For this purpose, this study used a total of 239 monthly data from January 2000 to November 2019 in Kookmin Bank housing statistics. In the correlation analysis, Korea showed the highest relationship in order of Seoul, Busan, Incheon and Daegu. Seoul showed a low figure of 0.3 without any distinctive features from other cities. On the other hand, Busan, Daejeon and Daegu showed high correlations. As a result of the regression analysis, Korea and 5 major cities were all moving in the same direction with positive(+) values. And Busan and Seoul responded significantly to Korea. In the shock response, Korea is most shocked by the change in Seoul. Daegu is relatively shocked by Busan and Daejeon. Seoul's charter rate has declined most strongly in the last three years. Therefore, it is time to be careful not to incur losses due to gap investment. If we look at the relationship between the charter rate and the sale price in future studies, we can better understand the Korean apartment market.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.13-25
• /
• 2016

High-speed railway (Korea Train Express) has had a deep impact on the regional economy of Korea. Current high-speed rail research is mostly theoretical, there is a lack of quantitative research using a precise algorithm to study the effect of high-speed railway on the regional economy. This paper analyses the influence of high-speed rail on the regional economy, with a focus on the Daegu area. Quantitative analysis using department store indexes and regional medical records is performed to calculate the economic influence of high-speed rail. The result shows that high-speed railway effects the regional economy though regional consumption growth and medical care trends.