DOI QR코드

DOI QR Code

한국 30~40대 실업률 예측을 위한 구글 검색 정보의 활용

Application of Google Search Queries for Predicting the Unemployment Rate for Koreans in Their 30s and 40s

  • 정재운 (동아대학교 경영정보학과) ;
  • 황진호 (동아대학교 경영정보학과)
  • Jung, Jae Un (Department of Management Information Systems, Dong-A University) ;
  • Hwang, Jinho (Department of Management Information Systems, Dong-A University)
  • 투고 : 2019.08.09
  • 심사 : 2019.09.20
  • 발행 : 2019.09.28

초록

장기불황으로 인해 한국 청년실업률이 수년간 10% 안팎의 높은 수준을 유지하고 있는 가운데, 주요 경제활동 인구인 30~40대의 실업률이 최근 상승세를 보이고 있다. 정부의 기존 청년 중심의 고용촉진 및 실업복지 정책을 30~40대를 포함한 다양한 연령층으로 확대 강화하기 위해서는 각 연령층에 대한 실업예측 모형 연구가 필요하다. 이에 본 연구에서는 한국 통계청 실업률 자료와 구글 검색어를 활용하여 한국 30~40대 연령층에 특화된 실업률 예측모형을 개발하고자 하였다. 실업률 자료와 계절성 자기회귀누적이동평균 모형을 활용하여 기초모형(Model 1)을 다중선형회귀 모형으로 추정하였으며, 개선된 모형을 구하고자 구글 검색 질의어 정보를 Model 1에 추가 활용하였다(Model 2). 그 결과, 30대와 40대 연령층 모두 구글 검색 질의어를 추가 활용한 Model 2가 Model 1보다 우수한 예측력을 보였다. 이는 웹 검색 질의어가 여전히 한국의 실업률 예측모형을 개선하는 데 유의미함을 의미한다. 본 연구는 실질적인 활용을 위해 추가적인 연구가 필요하지만, 연령대별 실업률 예측 연구에 기여할 것으로 판단된다.

Prolonged recession has caused the youth unemployment rate in Korea to remain at a high level of approximately 10% for years. Recently, the number of unemployed Koreans in their 30s and 40s has shown an upward trend. To expand the government's employment promotion and unemployment benefits from youth-centered policies to diverse age groups, including people in their 30s and 40s, prediction models for different age groups are required. Thus, we aimed to develop unemployment prediction models for specific age groups (30s and 40s) using available unemployment rates provided by Statistics Korea and Google search queries related to them. We first estimated multiple linear regressions (Model 1) using seasonal autoregressive integrated moving average approach with relevant unemployment rates. Then, we introduced Google search queries to obtain improved models (Model 2). For both groups, consequently, Model 2 additionally using web queries outperformed Model 1 during training and predictive periods. This result indicates that a web search query is still significant to improve the unemployment predictive models for Koreans. For practical application, this study needs to be furthered but will contribute to obtaining age-wise unemployment predictions.

키워드

참고문헌

  1. J. M. Lovati. (1976). The Unemployment Rate as an Economic Indicator, Review, Issue Sep, 58(9), 2-9.
  2. Unemployment: Its Measurement and Types(Online). https://www.rba.gov.au/education/resources/explainers/unemployment-its-measurement-and-types.html
  3. Economically Active Population Survey(Online). http://kostat.go.kr/portal/eng/surveyOutline/4/1/index.static
  4. K. Choi. (2017). Why Korea's Youth Unemployment Rate Rises, KDI Focus, 88.
  5. Statistics Korea(Online). http://www.index.go.kr
  6. Y. S. Kim. (2018). Korea's Unemployment, GDP Growth Enter Critical Phase. The Korea Herald(Online). http://www.koreaherald.com/view.php?ud=20181220000289
  7. J. Burton. (2019). Solution to Korea Jobless Owes. Koreatimes.(Online). http://www.koreatimes.co.kr/www/opinion/2019/03/396_265537.html
  8. H. J. Lee. (2018). Gov't Spends Big to Reduce Rate of Youth Unemployment. Korea Joongang Daily(Online). http://koreajoongangdaily.joins.com/news/article/article.aspx?aid=3045660
  9. N. Askitas & K. F. Zimmermann. (2009). Google Econometrics and Unemployment Forecasting, Applied Economics Querterly, 55(2), 107-120. DOI : 10.3790/aeq.55.2.107
  10. H. Choi & H. Varian. (2009). Predicting Initial Claims for Unemployment Benefits(Online). https://static.googleusercontent.com/media/research.google.com/ko//archive/papers/initialclaimsUS.pdf
  11. C. Anvik & K. Gjelstad. (2010). Just Google It: Forecasting Norwegian Unemployment Figures with Web Queries, Master's Thesis, BI Norwegian School of Management.
  12. C. M. Kwon, S. W. Hwang & J. U. Jung. (2015). Application of Web Query Information for Forecasting Korean Unemployment Rate. Journal of the Korea Society for Simulation, 24(2), 31-39. DOI : 10.9709/JKSS.2015.24.2.031
  13. C. M. Kwon & J. U. Jung. (2016). Forecasting Youth Unemployment in Korea with Web Search Queries. LNCS 9870, 3-14. DOI : 10.1007/978-3-319-46301-8_1
  14. J. U. Jung. (2018). Comparative Usefulness of Naver and Google Search Information in Predictive Models for Youth Unemployment Rate in Korea. Journal of Digital Convergence, 16(8), 169-179. DOI : 10.14400/JDC.2018.16.8.169
  15. J. Fuchs, D. Sohnlein, B. Weber & E. Weber. (2017). Forecasting Labour Supply and Population: An Integrated Stochastic Model, IAB-Disscussion Paper, 1/2017.(Online). http://doku.iab.de/discussionpapers/2017/dp0117.pdf
  16. Korean Statistical Information Service(Online). www.kosis.kr
  17. C. D. Montgomery, L. C. Jennings & M. Kulahci. (2008). Introducing to Time Series Analysis and Forecasting, Wiley-Interscience: Hoboken.
  18. E. P. B. Box, G. M. Jenkins, G. C. Reinsel & G. M. Ljung. (2015). Time Series Analysis: Forecasting and Control, Wiley: Hoboken.
  19. R. Nau. (2019). Statistical Forecasting: Notes on Regression and Time Series Analysis(Online). https://people.duke.edu/-rnau/411home.htm
  20. R. Hyndman. (2019). Auto.arima. RDocumentation(Online). https://www.rdocumentation.org/packages/forecast/versions/8.7/topics/auto.arima
  21. Google Trends(Online). https://trends.google.com