• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.47-56
• /
• 2020

The stock index is used not only as an economic indicator for a country, but also as an indicator for investment judgment, which is why research into predicting the stock index is ongoing. The task of predicting the stock price index involves technical, basic, and psychological factors, and it is also necessary to consider complex factors for prediction accuracy. Therefore, it is necessary to study the model for predicting the stock price index by selecting and reflecting technical and auxiliary factors that affect the fluctuation of the stock price according to the stock price. Most of the existing studies related to this are forecasting studies that use news information or macroeconomic indicators that create market fluctuations, or reflect only a few combinations of indicators. In this paper, this we propose to present an effective combination of the news information sentiment analysis and various macroeconomic indicators in order to predict the US Dow Jones Index. After Crawling more than 93,000 business news from the New York Times for two years, the sentiment results analyzed using the latest natural language processing techniques BERT and NLTK, along with five macroeconomic indicators, gold prices, oil prices, and five foreign exchange rates affecting the US economy Combination was applied to the prediction algorithm LSTM, which is known to be the most suitable for combining numeric and text information. As a result of experimenting with various combinations, the combination of DJI, NLTK, BERT, OIL, GOLD, and EURUSD in the DJI index prediction yielded the smallest MSE value.

• Korean Journal of Social Welfare
• /
• v.55
• /
• pp.155-179
• /
• 2003

This paper compares two indicators, economic development and social condition, to find a better way to measure the level of social welfare development. The results show that social condition is more adequate indicator than economic development. The social condition has high correlation with the development of social welfare in all the 78 countries as well as in five groups of countries when the economic development is controlled. The comparison of two indicators reveals important findings. Among other things, the higher the level of social condition compared with economic development, the larger the social welfare expenditure. This tendency is particularly strong among the western European countries and former socialist countries. This result implies that the macro-level policy of social redistribution is also important for the development of social welfare in addition to micro-level policy of income redistribution. As we expected, the results show that the level of Korean social welfare development is very low. Considering our levels of economic development and social condition, predicted social welfare expenditure from regression model is at least 17% of GDP, but we are spending only 30% of this predicted expenditure. Another serious problem in Korean social welfare is unbalanced expenditure between social insurance and public assistance. On the basis of these results, this paper suggests three implications for social policy to improve Korean social welfare: First of all, the gap between predicted and actual expenditures should be closed to improve the minimum level of social welfare. Secondly, the level of social condition itself should be improved to increase the public awareness of social welfare. Finally, the wide difference in expenditure between universal and selective social welfare programs should also be removed to decrease the relative deprivation of the poor.

• Journal of Labour Economics
• /
• v.25 no.1
• /
• pp.97-129
• /
• 2002

It is well known that the quality of job match has strong influence on the efficient allocation of labor resources in the economy on the macro level and also on the productivity of individual worker. Regarding this point we assumed that the selection of preferred job at the job entry can be interpreted as a subjective indicator of job match quality and tried to estimate the effects of such selection on the wage level. For this purpose we suggested random effects switching regression model and applied this model to the data of the Korea Labor Institute Panel Study from 1998 to 2000. As the results of estimation, we found that there exists large wage differentials at least more than fifty percent caused by such selection. Considering the fact that such wage differentials can not be suitably explained by the traditional reasons of the wage discrimination, we suggest the possibility that there also exists large productivity gap caused by the job mismatch and the necessity of improving the job placement service activity.

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.1
• /
• pp.99-110
• /
• 2020

Productivity is also a very important indicator in the construction industry as it can measure economic growth and the efficiency of each related production activity, either at the industrial level or at the corporate level. Technical factors indeed have a great impact on productivity, but in order to improve productivity in the actual construction industry, various productivity factors must be analyzed first, and the efforts to improve productivity at the project level are more important than the efforts to improve productivity at the construction industry level, which are addressed from a macro perspective. This study was designed to provide basic data for efficient productivity management activities of the project by selecting priority management factors through the causal analysis of the factors and the elicitation of the productivity degradation factors at the construction site to improve the quality of the construction industry.