• 무역학회지
• /
• 제46권1호
• /
• pp.169-187
• /
• 2021

This paper analyzes the feasibility of using machine learning and deep learning methods to forecast the income and employment using the strategic industries as well as investment, export, and exchange rates. The decision tree, artificial neural network, support vector machine, and deep learning models were used to forecast the income and employment in Busan. The following were the main findings of the comparison of their predictive abilities. First, the decision tree models predict the income and employment well. The forecasting values for the income and employment appeared somewhat differently according to the depth of decision trees and several conditions of strategic industries as well as investment, export, and exchange rates. Second, since the artificial neural network models show that the coefficients are somewhat low and RMSE are somewhat high, these models are not good forecasting the income and employment. Third, the support vector machine models show the high predictive power with the high coefficients of determination and low RMSE. Fourth, the deep neural network models show the higher predictive power with appropriate epochs and batch sizes. Thus, since the machine learning and deep learning models can predict the employment well, we need to adopt the machine learning and deep learning models to forecast the income and employment.

• 무역학회지
• /
• 제46권2호
• /
• pp.281-299
• /
• 2021

This paper analyzes the feasibility of using machine learning methods to forecast the employment. The machine learning methods, such as decision tree, artificial neural network, and ensemble models such as random forest and gradient boosting regression tree were used to forecast the employment in Busan regional economy. The following were the main findings of the comparison of their predictive abilities. First, the forecasting power of machine learning methods can predict the employment well. Second, the forecasting values for the employment by decision tree models appeared somewhat differently according to the depth of decision trees. Third, the predictive power of artificial neural network model, however, does not show the high predictive power. Fourth, the ensemble models such as random forest and gradient boosting regression tree model show the higher predictive power. Thus, since the machine learning method can accurately predict the employment, we need to improve the accuracy of forecasting employment with the use of machine learning methods.

• Communications for Statistical Applications and Methods
• /
• 제26권5호
• /
• pp.497-506
• /
• 2019

Forecasting the U.S. employment level is made using machine learning methods of the artificial neural network: deep neural network, long short term memory (LSTM), gated recurrent unit (GRU). We consider the big data of the federal reserve economic data among which 105 important macroeconomic variables chosen by McCracken and Ng (Journal of Business and Economic Statistics, 34, 574-589, 2016) are considered as predictors. We investigate the influence of the two statistical issues of the dimension reduction and time series differencing on the machine learning forecast. An out-of-sample forecast comparison shows that (LSTM, GRU) with differencing performs better than the autoregressive model and the dimension reduction improves long-term forecasts and some short-term forecasts.

• 한국항만학회지
• /
• 제11권2호
• /
• pp.305-320
• /
• 1997

The objective of this paper is to analysis & forecast on the change in spatial structures of southeast region by development of the Seoul-Pusan high-speed Rail. To measure the spatial structures, it was used the method of mean center and standard distance among of centrographic measures as analytical tools. The changes of spatial structures patten over time and space in the southeast region were surveyed using population and employment data of 57 zones. And also, to forecast the spatial structures of the southeast region after opening of the Seoul-Pusan high-speed rail, it was supposed three(3) scenarios which designed using influential area with centering around of the proposed high-speed rail stations. Therefore, the results of this research indicate as follows; 1) The spatial structures of population is showed a trend of continual concentration toward Ulsan city area, and also the spatial structures of employment is showed a trend of continual dispersion over time. 2) The forecast of three93) scenarios supposed after opening of the Seoul-Pusan high-speed rail in 2006 show a change of the spatial structures with both population concentration and employment dispersion. In the meantime, the rapid increase of population and wide dispersion of employment is reform with centering around HSR stations which builted in the southeast region after opening of high-speed rail. 3) It shall furnish valuable data to establish the development strategy of urban and local region, and also forecast the change of spatial structures about population and employment in influential area which passed on high-speed rail line & stations by method of mean center and standard distance among of centrographic measures as analytical tools.

• 한국융합학회논문지
• /
• 제11권11호
• /
• pp.257-267
• /
• 2020

본 연구는 우리나라 수출 분야의 산업별 고용비중을 다양한 머신러닝 기법을 활용하여 예측하고, 예측성능을 높이기 위하여 머신러닝 기법 예측값들에 예측조합 기법을 적용하였다. 특히, 본 연구에서는 각 머신러닝 기법 예측값들에 부여되는 가중치의 합을 1로 설정하는 제약하의 예측조합 기법을 사용하여 예측의 정확성과 안정성을 확보하고자 하였다. 또한, 본 연구는 산업별 고용비중에 영향을 주는 다양한 변수를 고려하기 위하여 재귀적특성제거 방법을 사용하여 주요 변수를 선별한 후, 머신러닝 기법에 적용함으로써 예측과정 상에서의 효율성을 높였다. 분석결과, 예측조합 방법에 따른 예측값은 머신러닝 기법의 예측값들보다 실제의 산업 고용비중에 근접한 것으로 나타났으며, 머신러닝 기법의 예측값들이 큰 변동성을 보이는 것과 달리 제약하의 예측조합 기법은 안정적인 예측값을 나타내었다.

• 한국융합학회논문지
• /
• 제13권5호
• /
• pp.237-247
• /
• 2022

본 연구는 급속한 고령화 시대에서 우리나라의 고령층의 경제활동 수준을 다양한 머신러닝 기법으로 정확히 예측하고자 하였다. 고령층의 경제활동 수준과 기존 연구들은 고령층의 삶의 만족도, 사회보장제도 등과 연관된 인과성 검증을 중심으로 이루어진 데 반해, 본 연구는 다양한 머신러닝 기법으로 고령층의 경제활동 수준을 예측하였으며, 특히 예측조합법을 함께 사용함으로써 예측의 안정성을 도모하였다. 60세 이상의 경제활동참가율, 취업률 등을 종속변수로 하고 가구 특성, 소득, 평균임금 등을 설명변수로 설정하여 서로 다른 특성을 지닌 5가지의 머신러닝 기법과 2가지의 예측조합법을 적용하여 예측결과들을 비교하였다. 분석 결과, 종속변수별, 예측구간별로 예측성능이 높은 머신러닝 기법 및 예측조합법은 상이하였으나, 예측의 안정성 측면에서는 예측조합법이 상대적으로 우수한 것으로 나타났다. 이에 따라, 본 연구는 고령층의 경제활동 수준을 정확히 예측하고 예측의 안정성을 도모하여 정책적 관점에서도 실용성을 제고한다고 볼 수 있다.

• 가정과삶의질연구
• /
• 제27권2호
• /
• pp.203-211
• /
• 2009

This study was conducted to evaluate a forecast model designed to describe a vocational high school for runaway students. The study included 2000 adolescents from the KEEP(Korean Education and Employment Panel). A Data mining decision tree model revealed that: (1) Suicide ideation was a risk factor for running away among smokers. (2) High self-evaluation was a risk factor for running away among individuals that smoked and had no suicide ideation. (3) Drinking was predicted as a risk factor for no smokers, while family life dissatisfaction was predicted as a risk factor among non-smokers that drank. (4) Negative relationship with mother was predicted as a risk factor among non-drinking non-smoking.

• 상하수도학회지
• /
• 제20권2호
• /
• pp.187-196
• /
• 2006

Forecasting the long-term water demand is important in the plan of water supply system because the location and capacity of water facilities are decided according to it. To forecast the long-term water demand, the existing method based on lpcd and population has been usually used. But, these days the trend among the variation of water demand has been disappeared, so expressing other variation of it is needed to forecast correct water demand. To accomplish it, we introduced the System Dynamics method to consider total connections of water demand factor. Firstly, the factors connected with water demand were divided into three sectors(water demand, industry, and population sectors), and the connections of factors were set with multiple regression model. And it was compared to existing method. The results are as followings. The correlation efficients are 0.330 in existing model and 0.960 in SD model and MAE are 3.96% in existing model and 1.68% in SD model. So, it is proved that SD model is superior to the existing model. To forecast the long-term water demand, scenarios were made with variations of employment condition, economic condition and consumer price indexes and forecasted water demands in 2012. After all scenarios were performed, the results showed that it was not needed to increase the water supply ability in Seoul.

• 대한가정학회지
• /
• 제47권5호
• /
• pp.67-77
• /
• 2009

This study examined risk factors and protective factors in high school students’ suicidal ideation. Participants were 2000 adolescents from the KEEP(Korean Education and Employment Panel). Data mining decision tree model revealed that: (1) Irrespective of sex, the most important predictor was father-adolescent relationship. (2) Positive mother-adolescent relationship was predicted as protective factor in condition of negative father-adolescent relationship. (3) Family activities was predicted as risk factor in condition of negative mother-adolescent relationship under the circumstances with negative father-adolescent relationship. (4) Low self-evaluation was predicted as risk factor in condition of serious agony about personality under the circumstances with positive father-adolescent relationship.

• 인터넷정보학회논문지
• /
• 제16권2호
• /
• pp.99-107
• /
• 2015

모든 산업이 ICT 인프라를 기반으로 융합되고 나아가 산업과 문화가 융합되는 스마트융합 환경이 도래함에 따라, ICT 인프라를 시공 및 구축하는 정보통신공사업이 중요하게 평가되고 있다. 이러한 정보통신공사업의 지속적인 성장을 위해서는 기술인력의 공급이 안정적으로 이루어지는 것이 매우 중요하나, 현재까지 이론적으로 체계적인 정보통신공사업 분야의 인력수급차 분석이 수행된 바가 없다. 특히 정부에서도 2014년 12월에 공사업 육성방안 로드맵을 추진하며 중장기 인력수급차 분석에 기반한 인적역량 강화방안을 모색하겠다고 발표하여, 정량적인 인력수급차 분석의 필요성은 더욱 중요해지는 상황이다. 이에 본 연구에서는 정보통신공사업의 인력수급 예측모형을 개발하고, 인력수급차 분석결과를 제시하였다. 분석결과, 2007년도부터 전문대학의 입학자 감소, 구조조정, 학과개편 등의 요인으로 전문대 교육과정에서 배출되는 졸업생이 줄어들어 초과수요상태가 나타나는 것으로 조사되었다. 이에 따라 정보통신공사업 시장의 기술인력 부족현상을 줄이기 위해, 기존인력의 재교육, 정보통신기술인력 양성정책을 지속적으로 유지하고 다양한 정책적 유인을 제공할 필요성이 있는 것으로 분석되었다.