• Korea Trade Review
• /
• v.46 no.1
• /
• 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.

• Korea Trade Review
• /
• v.46 no.2
• /
• 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.

• Journal of Digital Convergence
• /
• v.16 no.3
• /
• pp.181-187
• /
• 2018

With a view to deepening the research stream on the factors positively influencing the export growth and the employment increase of South Korean small and medium companies, this research has developed the research model about the impact of small and medium companies' external technology R&D collaboration network heterogeneity on their export growth and employment increase, and has empirically tested the research model with the 2,200 data collected from the small and medium companies in the South Korea. This study illuminates the two points from the empirical testing results. One point is that small and medium companies' external technology R&D collaboration network heterogeneity significantly and positively influences their employment increase from technology development. The other point is that small and medium companies' export growth from technology R&D partially mediates the impact of the external technology R&D collaboration network heterogeneity on their employment increase from technology R&D.

• Journal of Korean Institute of Industrial Engineers
• /
• v.39 no.4
• /
• pp.278-289
• /
• 2013

Up-to-date market dynamics and intense competition have forced a production system to be more widely distributed and decentralized than ever, and the production system itself can be regarded as a collaborative network of autonomous production resources in which the responsibility of decision making is also decentralized into individual autonomous entities. The conventional resource management models, however, are not suitable for the distributed and decentralized environment because of their centralized nature. In this paper, an agent-based resource management model is proposed. The proposed model applies employment relation-driven fractal organization (FrOrg) into organizational model for distributed production resources and presents a resource management framework based on employment contracts. The fractal organization is a structured association in which a self-similar pattern recursively appears, and employment relations between production resources are recursively constructed throughout the entire production system.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.303-307
• /
• 2022

The purpose of the study is to determine the key aspects of the problems of employment of the population and the directions of their state regulation in war conditions. Employment policy involves a system of measures to create conditions for a more complete use of the potential of labor and business activity of the able-bodied population, linking this activity through taking into account the specifics of group interests with the tasks and guidelines for socio-economic development. But in the conditions of war, this problem acquires a new relevance. For the study, a number of theoretical methods of analysis were used. Based on the results of the study, the key aspects of the problems of employment of the population and the directions of their state regulation in war conditions were identified.

• Korean Journal of Social Welfare
• /
• v.63 no.2
• /
• pp.261-289
• /
• 2011

This study has been conducted to assess the effectiveness of the elderly employment programs through change of social capital by understanding how the elderly employment programs in the elderly employment policy of Korea has effected the change of social capital. The method of research was to design the research in the nonequivalent control groups design from the quasi-experimental design for the 500 elderly who participated and 250 who have not participated in the elderly employment programs through distributing structured questionnaire by classifying into before and after the project during 7 months from March 1, 2010 to September 30, 2010 to those above 65 living in Changwon. The social capital which is an important variable among the measurement index of the study has been set as trust, network, and social participation fields based on the aforementioned theoretic background. When the fact that there is a partial difference in the change of social capital of the elderly according to the participation in the elderly employment programs and the timing (before/after) is looked at in terms of change of social capital after controlling the general character of the elderly and the pre-score, there are differences per timing according to the participation in the elderly employment programs. Thus, the participation in the elderly employment programs had a significant difference in the change of social capital. It is possible to see that the trust, network, and social participation of the social capital all increased in the elderly with difficulties in their living status. It can be seen that the participation in the elderly employment programs brings forth increase of social capital for the elderly with difficulties in their living status. Among the social capitals, the elderly who participated in the elderly employment programs showed that the trust increased the most. Consequently, in order to increase the comprehensive social capital, the programs must be carried out focused on the vulnerable class in parallel to the elderly employment programs for the general elderly of other classes.

• Communications for Statistical Applications and Methods
• /
• v.26 no.5
• /
• 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.

• International Journal of Computer Science & Network Security
• /
• v.21 no.5
• /
• pp.160-167
• /
• 2021

The authors of the article investigate the impact of digitalization on the forms change of employment and the labor market in the modern conditions. It is substantiated that digitalization processes directly affect the change of forms of employment and the range of occupations in the labor market, as well as the change of jobs. The positive and negative consequences of changing forms of employment for the economy in the process of digital transformation are analyzed, which include: reduction of personnel costs by employers; dissemination of non-standard, informal employment (electronic freelance, electronic outsourcing, start-employment); enabling employees to manage their working hours; increasing unemployment and imbalance of supply and demand in the labor market; reduction of productivity of enterprises, as a result of reduced productivity of workers with non-standard forms of employment, or with a negative indirect impact on productivity. A model for managing the process of digitalization in the labor market of Ukraine under different scenarios of their implementation, namely evolutionary and forced is devoted. To recognize the possible change in the level of employment in connection with the implementation of the forced scenario of digitalization in Ukraine, a model for estimating probable changes in the labor market is proposed. The directions of development of the state strategy of prevention of risks of reduction of number of workplaces in the course of digitalization are outlined.

• Korean Journal of Social Welfare
• /
• v.46
• /
• pp.427-458
• /
• 2001

The present study is designed to trace the successful reform steps taken within the employment support system in the UK and to extract a set of instructive implications for Korea's future reform path towards an efficient employment support system conductive to youth employment by setting out an analytical framework that links the British experience to the Korean context. To this end, this study focuses on three major aspects of employment support system: delivery mechanism, method of delivery, and programs. Implications drawn from the comparative analysis are as follows. First, the current employment support services in Korea-including job placement service, vocational training, and public works-should be more tightly integrated and delivered in a more consistent fashion in order to become highly accessible to the unemployed. Second, the cooperative network between employment service providers and the corporate sector as demander of labor should be institutionalized in order to make the employment support system more responsive to labor demand. Third, to create an enhanced employment support system that counts in individual differences of the unemployed would require continued, in-depth consultation and case management services along with fully specialized employment caseworkers who would provide them. Fourth, the government should take the initiative and be unflaggingly supportive both institutionally and financially in making future efforts to continuously improve the employment support system on the basis of the implications mentioned above.

• Korean Journal of Human Ecology
• /
• v.23 no.6
• /
• pp.1105-1126
• /
• 2014

The purpose of this study was to explore the factors related to depression of married baby-boomer female by employment status. Data for this study was based on a convenience sample of 499 married female baby-boomer who have residence in Busan and Gyeongnam province. The prevalence rate of depression symptoms was 21.4%. The employment status made differences on the factors related to depression of married female baby boomers. Depressive symptoms were significantly associated with attitudes toward menopause, menopausal symptoms and marital satisfaction for both baby-boomer female with and without a job. While monthly household income, participation in voluntary associations and satisfaction with children were significantly related to depression symptoms of baby-boomer female without employment, perimenopausal stage, perceived size of social network was important factors for the depression of married female baby boomers with a job.