설명 가능한 인공지능을 이용한 지역별 출산율 차이 요인 분석
Analysis of Regional Fertility Gap Factors Using Explainable Artificial Intelligence
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Korea is facing a significant problem with historically low fertility rates, which is becoming a major social issue affecting the economy, labor force, and national security. This study analyzes the factors contributing to the regional gap in fertility rates and derives policy implications. The government and local authorities are implementing a range of policies to address the issue of low fertility. To establish an effective strategy, it is essential to identify the primary factors that contribute to regional disparities. This study identifies these factors and explores policy implications through machine learning and explainable artificial intelligence. The study also examines the influence of media and public opinion on childbirth in Korea by incorporating news and online community sentiment, as well as sentiment fear indices, as independent variables. To establish the relationship between regional fertility rates and factors, the study employs four machine learning models: multiple linear regression, XGBoost, Random Forest, and Support Vector Regression. Support Vector Regression, XGBoost, and Random Forest significantly outperform linear regression, highlighting the importance of machine learning models in explaining non-linear relationships with numerous variables. A factor analysis using SHAP is then conducted. The unemployment rate, Regional Gross Domestic Product per Capita, Women's Participation in Economic Activities, Number of Crimes Committed, Average Age of First Marriage, and Private Education Expenses significantly impact regional fertility rates. However, the degree of impact of the factors affecting fertility may vary by region, suggesting the need for policies tailored to the characteristics of each region, not just an overall ranking of factors.
Abstract
Korea is facing a significant problem with historically low fertility rates, which is becoming a major social issue affecting the economy, labor force, and national security. This study analyzes the factors contributing to the regional gap in fertility rates and derives policy implications. The government and local authorities are implementing a range of policies to address the issue of low fertility. To establish an effective strategy, it is essential to identify the primary factors that contribute to regional disparities. This study identifies these factors and explores policy implications through machine learning and explainable artificial intelligence. The study also examines the influence of media and public opinion on childbirth in Korea by incorporating news and online community sentiment, as well as sentiment fear indices, as independent variables. To establish the relationship between regional fertility rates and factors, the study employs four machine learning models: multiple linear regression, XGBoost, Random Forest, and Support Vector Regression. Support Vector Regression, XGBoost, and Random Forest significantly outperform linear regression, highlighting the importance of machine learning models in explaining non-linear relationships with numerous variables. A factor analysis using SHAP is then conducted. The unemployment rate, Regional Gross Domestic Product per Capita, Women's Participation in Economic Activities, Number of Crimes Committed, Average Age of First Marriage, and Private Education Expenses significantly impact regional fertility rates. However, the degree of impact of the factors affecting fertility may vary by region, suggesting the need for policies tailored to the characteristics of each region, not just an overall ranking of factors.
참고문헌 (20)
- Bae, G. R., "Comparative Analysis of Low Fertility Policy and the Public Perceptions using Text-Mining Methodology", Journal of Digital Convergence, 19(12), pp.29~42 (2021)
- Boser, B. E., "A training algorithm for optimal margin classifiers", Proceedings of the fifth annual workshop on Computational learning theory, pp.144~152 (1992)
- Breiman, L., "Random forests", Machine Learning, 45, pp.5~32 (2001)
- Chen, T., "Xgboost: A scalable tree boosting system", Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, pp.785~794 (2016)
- Study on Causes of Low Birthrate in Gyeonggi Province and Forecasting Birth Trends, "Cho, Y. T.", Graduate School of Public Health, Seoul National University, ~ (2016)
- Choi, S. M., "Analysis of Factors Influencing the fertility rate of metropolitan governments : Focusing on economic and policy factors", Journal of Governance Studies, 16(4), pp.65~100 (2021)
- "Explainable Artificial Intelligence (XAI)"[URL]
- Ha, J. K., "An Economic Analysis of Low Fertility in Korea: Focusing on Income Inequality and Cost of Education", The Review of Social&Economic Studies, (39), pp.137~174 (2012)
- Joo, S. M., "Forecasting Birthrate Change based on Big Data", Informatization Policy, 26(4), pp.20~35 (2019)
- Kim, B. R., "Explainable Artificial Intelligence(XAI)technology that goes beyond the limitations of medical artificial intelligence", Korea Health Industry Development Institute, 340, pp.5~10 (2021)
- Kim, K. A., "An Analysis of Factors Affecting the Birth Rate of Married Women", Culture and Convergence, 39(6), pp.895~924 (2017)
- Korea Institute of Public Finance, "Policy Design Using Machine Learning : Focusing on the Determinants of Childbirth", Financial Forum, 279, pp.12~35 (2019)
- Lee, C. H., "Did Pro-natal Policy in Korea Fail? : A Decomposition of Fertility Change from 2000 to 2016", The Korean Journal of Economic Studies, 66(3), pp.5~42 (2018)
- Ministry of National Defense, "Defense White Paper 2016" (2016)
- 2019~2050 NABO long-term financial outlook, "NABO", ~ (2019)
- Oh, S. W., "Factors Influencing the Fertility Rate by Local Government in Korea: Focused on Socio-cultural Factors, Economic Factors, and Policy Factors", Public Policy Review, 32(1), pp.55~81 (2018)
- Park, E. J. L., "KoNLPy: Korean natural language processing in Python", Proceedings of the 26th Annual Conference on Human & Cognitive Language Technology, 6 (2014)
- Park, S. M., "KNU Korean Sentiment Lexicon : Bi-LSTM-based Method for Building a Korean Sentiment Lexicon", Journal of Intelligence and Information Systems, 4, pp.219~240 (2018)
- Population trend survey, "Statistics Korea", ~ (2022)
- Won, S. Y., "The Determinants of the Fertility Rate of Local Government in Korea : Focusing on Factors related to the Cost for Children", The Korea Association for Policy Studies, 27(3), pp.231~268 (2018)