• International journal of advanced smart convergence
• /
• v.11 no.1
• /
• pp.19-27
• /
• 2022

Across the world, 'housing' comprises a significant portion of wealth and assets. For this reason, fluctuations in real estate prices are highly sensitive issues to individual households. In Korea, housing prices have steadily increased over the years, and thus many Koreans view the real estate market as an effective channel for their investments. However, if one purchases a real estate property for the purpose of investing, then there are several risks involved when prices begin to fluctuate. The purpose of this study is to design a real estate price 'return rate' prediction model to help mitigate the risks involved with real estate investments and promote reasonable real estate purchases. Various approaches are explored to develop a model capable of predicting real estate prices based on an understanding of the immovability of the real estate market. This study employs the LSTM method, which is based on artificial intelligence and deep learning, to predict real estate prices and validate the model. LSTM networks are based on recurrent neural networks (RNN) but add cell states (which act as a type of conveyer belt) to the hidden states. LSTM networks are able to obtain cell states and hidden states in a recursive manner. Data on the actual trading prices of apartments in autonomous districts between January 2006 and December 2019 are collected from the Actual Trading Price Disclosure System of the Ministry of Land, Infrastructure and Transport (MOLIT). Additionally, basic data on apartments and commercial buildings are collected from the Public Data Portal and Seoul Metropolitan Government's data portal. The collected actual trading price data are scaled to monthly average trading amounts, and each data entry is pre-processed according to address to produce 168 data entries. An LSTM model for return rate prediction is prepared based on a time series dataset where the training period is set as April 2015~August 2017 (29 months), the validation period is set as September 2017~September 2018 (13 months), and the test period is set as December 2018~December 2019 (13 months). The results of the return rate prediction study are as follows. First, the model achieved a prediction similarity level of almost 76%. After collecting time series data and preparing the final prediction model, it was confirmed that 76% of models could be achieved. All in all, the results demonstrate the reliability of the LSTM-based model for return rate prediction.

• Information Systems Review
• /
• v.22 no.4
• /
• pp.21-39
• /
• 2020

Recently, deep learning has shown high performance in various applications such as pattern analysis and image classification. Especially known as a difficult task in the field of machine learning research, stock market forecasting is an area where the effectiveness of deep learning techniques is being verified by many researchers. This study proposed a deep learning Convolutional Neural Network (CNN) model to predict the direction of stock prices. We then used the feature selection method to improve the performance of the model. We compared the performance of machine learning classifiers against CNN. The classifiers used in this study are as follows: Logistic Regression, Decision Tree, Neural Network, Support Vector Machine, Adaboost, Bagging, and Random Forest. The results of this study confirmed that the CNN showed higher performancecompared with other classifiers in the case of feature selection. The results show that the CNN model effectively predicted the stock price direction by analyzing the embedded values of the financial data

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• Journal of Energy Engineering
• /
• v.23 no.4
• /
• pp.31-40
• /
• 2014

The Korean government made the 2nd Energy Basic Plan to achieve 11% of new and renewable energies distribution rate until 2035 as a response to cope with international discussion about greenhouse gas emission reduction. Renewable energies include solar thermal, photovoltaic, bioenergy, wind power, small hydropower, geothermal energy, ocean energy, and waste energy. New energies contain fuel cells, coal gasification and liquefaction, and hydrogen. As public and private investment to enhance the distribution of new and renewable energies, it is necessary to clarify the economic effects of the new and renewable energies sector. To the end, this study attempts to apply an input-output analysis and analyze the economic effects of new and renewable energies sector using 2012 input-output table. Three topics are dealt with. First, production-inducing effect, value-added creation effect, and employment-inducing effect are quantified based on demand-driven model. Second, supply shortage effects are analyzed employing supply-driven model. Lastly, price pervasive effects are investigated applying Leontief price model. The results of this analysis are as follows. First, one won of production or investment in new and renewable energies sector induces 2.1776 won of production and 0.7080 won of value-added. Moreover, the employment-inducing effect of one billion won of production or investment in new and renewable energies sector is estimated to be 9.0337 persons. Second, production shortage cost from one won of supply failure in new and renewable energies sector is calculated to be 1.6314 won, which is not small. Third, the impact of the 10% increase in new and renewable energies rate on the general price level is computed to be 0.0123%, which is small. This information can be utilized in forecasting the economic effects of new and renewable energies sector.

• The Journal of Information Systems
• /
• v.26 no.3
• /
• pp.171-185
• /
• 2017

Purpose Recently, there has been an increase in attempts to analyze social phenomena, consumption trends, and consumption behavior through a vast amount of customer data such as web search traffic information and social buzz information in various fields such as flu prediction and real estate price prediction. Internet portal service providers such as google and naver are disclosing web search traffic information of online users as services such as google trends and naver trends. Academic and industry are paying attention to research on information search behavior and utilization of online users based on the web search traffic information. Although there are many studies predicting social phenomena, consumption trends, political polls, etc. based on web search traffic information, it is hard to find the research to explain and predict tourism demand and establish tourism policy using it. In this study, we try to use web search traffic information to explain the tourism demand for major cities in Gangwon-do, the representative tourist area in Korea, and to develop a nowcasting model for the demand. Design/methodology/approach In the first step, the literature review on travel demand and web search traffic was conducted in parallel in two directions. In the second stage, we conducted a qualitative research to confirm the information retrieval behavior of the traveler. In the next step, we extracted the representative tourist cities of Gangwon-do and confirmed which keywords were used for the search. In the fourth step, we collected tourist demand data to be used as a dependent variable and collected web search traffic information of each keyword to be used as an independent variable. In the fifth step, we set up a time series benchmark model, and added the web search traffic information to this model to confirm whether the prediction model improved. In the last stage, we analyze the prediction models that are finally selected as optimal and confirm whether the influence of the keywords on the prediction of travel demand. Findings This study has developed a tourism demand forecasting model of Gangwon-do, a representative tourist destination in Korea, by expanding and applying web search traffic information to tourism demand forecasting. We compared the existing time series model with the benchmarking model and confirmed the superiority of the proposed model. In addition, this study also confirms that web search traffic information has a positive correlation with travel demand and precedes it by one or two months, thereby asserting its suitability as a prediction model. Furthermore, by deriving search keywords that have a significant effect on tourism demand forecast for each city, representative characteristics of each region can be selected.

• Journal of Korean Society of Forest Science
• /
• v.81 no.3
• /
• pp.255-262
• /
• 1992

Urguay Round(UR) has lots of implication in the forest product market as well as the other sectors of the economy. Chestnut, one of the major forest product in Korea, would be affected by free trade resulting from the agreement on UR. To establish effective policy measures dealing with negative effects of free trade, if any, the effect of UR on producers should be figured out. In this contest, the purposes of this study are (1) estimating the demand, supply and its price functions of this market and (2) forecasting the effect of UR on growers. Using econometric method, demand, supply and price function of this market are estimated. The total amount of yearly money loss of growers due to free trade from 1992 to 2001 are estimated for four different scenarios. In each scenario, it is assumed that the tariffication reduction is 30%, 40%, 50% and 90%. Yearly money loss of chestnut growers at the year 2001 are forecasted such as 14 billion won, 18 billion won, 24 billion won and 25 billion won for the rate of tariffication reduction of 30%, 40%, 50%, and 90%, respectively.

• Journal of Korea Port Economic Association
• /
• v.28 no.4
• /
• pp.193-207
• /
• 2012

The of purpose of this study is to predict export and import container volumes using a Decision Tree analysis. Factors which can influence the volume of container cargo are selected as independent variables; producer price index, consumer price index, index of export volume, index of import volume, index of industrial production, and exchange rate(won/dollar). The period of analysis is from january 2002 to December 2011 and monthly data are used. In this study, CRT(Classification and Regression Trees) algorithm is used. The main findings are summarized as followings. First, when index of export volume is larger than 152.35, monthly export volume is predicted with 858,19TEU. However, when index of export volume is between 115.90 and 152.35, monthly export volume is predicted with 716,582TEU. Second, when index of import volume is larger than 134.60, monthly import volume is predicted with 869,227TEU. However, when index of export volume is between 116.20 and 134.60, monthly import volume is predicted with 738,724TEU.

• Journal of Technology Innovation
• /
• v.14 no.1
• /
• pp.227-254
• /
• 2006

Under the recent trend of telecommunications and broadcasting convergence, much more various forms of new convergence broadcasting services are being introduced than ever before. Owing to the unique advantages, new convergence broadcasting services are expected to bring drastic changes to the current broadcasting service market. In this research, we attempt to examine what kind of attributes critically affect the competition among new convergence broadcasting services, and how much competitive they will be, based on the quantitative information about consumer preferences for the important attributes of new convergence broadcasting services. Conjoint survey was used in order to obtain stated preference data of consumers. From the results, some implications are obtained as follows. First, even though new convergence broadcasting services have many unique advantages, still price is the most important for the consumers. Second, it is expected that considerable consumer valuation exists for the unique advantages of new convergence broadcasting services like mobility and dual-way interactivity, which will add the competitiveness of those services in the future. Third, since midterm advertising puts negative utility on consumers, broadcasting services with midterm advertising will not be preferred to those with neither advertising nor midterm advertising. Fourth, service coverage and the number of consumers using the same broadcasting service have a significant feedback effect on the competition between broadcasting services from the dynamic aspect. Lastly, the consumer preference can be affected by demographic variables like age and gender, and broadcasting service usage patterns such as channel switchover for escaping advertisement and frequency of using other recorded media. Main findings of our research might become useful information for both telecommunication and broadcasting companies, contents providers, advertisers, and policy and regulation makers to cope with the uncertain environment of telecommunication and broadcasting convergence.

• Health Policy and Management
• /
• v.21 no.3
• /
• pp.425-456
• /
• 2011

Background: Organizations in the pharmaceutical industry are highly dependent on the institutional environment. The introduction of pharmacoeconomics to the decision-making on the price and reimbursement decisions became strong constraints to pharmaceutical companies in Korea. As little is known about the issue on organization-environment interaction in the healthcare field, this study aimed to figure out how pharmaceutical companies adapted to the environmental changes. Methods: A multicase study method was used, selecting eight cases among multi-national pharmaceutical companies in South Korea. In-depth interviews were conducted with the managers of these organizations, and secondary data were reviewed to complement the interviews. Results: Pharmaceutical companies viewed the new policies as a big threat and sought for actions against them. One of the most distinguishing organizational changes was to construct a Market Access department. Other strategies managing the environment such as co-optation, forecasting, and bargaining were also implemented. These changes were consistent with the predictions of Resource Dependency Theory and Institutional Theory. Conclusions: The interactions between pharmaceutical companies and institutional environments in healthcare were first explored. This study presents a new perspective on how organizations change and the motives for the changes. The findings of this case study will form the basis of further empirical studies.

• Korean Journal of Construction Engineering and Management
• /
• v.4 no.4 s.16
• /
• pp.212-219
• /
• 2003

In construction project planning and control, a cost model performs a critical role such as cost determination on a contract stage and cost tracing. The model can maximize owner's profit and value within the project budget and optimize cost management works on overall construction implementation stages. A BoQ(Bill of Quantities) generally adopted in a unit price contract has been applied as an important tool for cost control and forecast. However a previous cost model based on the BoQ has shown limitations in that it requires too detailed information and heavy manpower on cost management and difficulty in keeping relationship with construction planning, scheduling and progress management. The each cost items and unit prices which constitute of construction works are individually very important management factors but the relative weight for each items and prices have a difference on the contents and conditions of each conditions of each construction works. In consideration of this structural mechanism of cost determination, this research is aimed at examining the critical factors affecting the construction cost determination and propose and verify a new cost forecasting model which is more simple and efficient and also keeps the accuracy of cost management.