Development of a Low Birth Rate Prediction Model Using Time-series and Machine Learning
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
(Purpose) The main goal of this study is to build a time-series prediction model to address Korea's low birth rate using machine learning and ARIMA models. It aims to predict future fertility trends and analyze socio-economic factors influencing birth rates with a focus on the MZ generation whose views on marriage and childbirth differ from previous generations. (Design/methodology/approach) This study utilizes machine learning models, including Linear Regression, Support Vector Machine (SVM), Random Forest, AdaBoost, Neural Networks, and the ARIMA time-series model. These models are trained on socio-economic data, analyzing variables like marriage rates, employment rates, and economic growth. The predictive accuracy of the models is evaluated using performance metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R² to forecast future birth rates. (Findings) The findings reveal that Neural Networks exhibited the highest predictive accuracy for future birth rates, with an R² of 0.978, followed by Linear Regression and SVM. The ARIMA model effectively forecasted long-term birth rate trends, demonstrating its suitability for analyzing time-series data. Socio-economic factors such as childcare subsidies, household income, and age at first marriage were found to significantly impact the fertility rate. (Research implications or Originality) This research combines machine learning models and time-series analysis to predict Korea's low birth rate. It is to highlight the need for policies that address both economic support and societal attitudes toward marriage and childbirth. It provides a framework for policymakers to design effective interventions and emphasizes the importance of non-linear relationships between socio-economic factors and birth rates, offering a novel approach in demographic studies.
Abstract
(Purpose) The main goal of this study is to build a time-series prediction model to address Korea's low birth rate using machine learning and ARIMA models. It aims to predict future fertility trends and analyze socio-economic factors influencing birth rates with a focus on the MZ generation whose views on marriage and childbirth differ from previous generations. (Design/methodology/approach) This study utilizes machine learning models, including Linear Regression, Support Vector Machine (SVM), Random Forest, AdaBoost, Neural Networks, and the ARIMA time-series model. These models are trained on socio-economic data, analyzing variables like marriage rates, employment rates, and economic growth. The predictive accuracy of the models is evaluated using performance metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R² to forecast future birth rates. (Findings) The findings reveal that Neural Networks exhibited the highest predictive accuracy for future birth rates, with an R² of 0.978, followed by Linear Regression and SVM. The ARIMA model effectively forecasted long-term birth rate trends, demonstrating its suitability for analyzing time-series data. Socio-economic factors such as childcare subsidies, household income, and age at first marriage were found to significantly impact the fertility rate. (Research implications or Originality) This research combines machine learning models and time-series analysis to predict Korea's low birth rate. It is to highlight the need for policies that address both economic support and societal attitudes toward marriage and childbirth. It provides a framework for policymakers to design effective interventions and emphasizes the importance of non-linear relationships between socio-economic factors and birth rates, offering a novel approach in demographic studies.
참고문헌 (25)
- An, Jeong-Hye, "Analysis of the Relationship Between Uncertainty and Childbirth : Focusing on Second childbirth Grant", The Korean Journal of Local Government Studies, 23(3), pp.159~182 (2019)[DOI]
- Bae, Eun-Kyung, "Seeking a Paradigm Shift in Population Policy by Raising Issues through the New Terminology of ‘Few Births’ : A Historical Review of the Aging Society and Population Policy in Korea and the Women’s Agency Related to Their Reproductive Bodies", Issues in Feminism, 21(2), pp.137~186 (2021)[DOI]
- Breiman, L., "Statistical modeling: The two cultures (with comments and a rejoinder by the author)", Statistical Science, 16(3), pp.199~231 (2001)[DOI]
- "Cope with Low Fertility: Policy Needs of MZ generation", The Journal of Korean Policy Studies, 22(1), pp.33~53
- Domestic Legal Information Division, Library of Congress, "A low birthrate society in data" (2024)
- oodfellow, I., "Deep learning" (2016), MIT Press
- Hastie, T., "The elements of statistical learning: Data mining, inference, and prediction" (2009), Springer
- Jo, Geun-Sic, "Comparative Analysis of Equity in Childcare Services in Low-Birth Rate Eras across Metropolitan Local Governments", Korean Comparative Government Review, 27(4), pp.109~133 (2023)
- Ju, Sang-Hyeon, "Issues and Policy Tasks for Local Governments to Respond to Low Fertility", Korean Comparative Government Review, 28(1), pp.205~230 (2024)
- Jung, Jae-Hoon, "A New Beginning in Response to the Low Fertility ‐ Transition from Population Policy to Family Policy ‐", Korean Journal of Family Social Work, 70(4), pp.215~234 (2023)[DOI]
- Kim, Min-Gon, "The Study of Policy Effectiveness about Childbirth Grant as Policies in Response to Low Birthrate: Focused on 25 Districts(Gu) in Seoul", Public Policy Review, 30(2), pp.163~190 (2016)
- Kim, Young-Sun, "Population Crisis Task Force, Reviewing government measures and supplementing legislation on low birth rates", National Assembly of the Republic of Korea, 16~17 (2024)
- "Statistics by subject" (2023)[URL]
- Lee, Sang-Yup, "A Study on the Machine Learning-Based Time Series Analysis and the Role of Local Universities on the Low Birth Problem in the Response to the Crisis of Local Extinction", Social Economy & Policy Studies, 14(2), pp.1~27 (2024)[DOI]
- Lutz, W., "Education rather than age structure brings demographic dividend", Proceedings of the National Academy of Sciences, 116(26), pp.12798~12803 (2019)[DOI]
- Mahesh, B., "Machine learning algorithms: A review", International Journal of Science and Research (IJSR) (2020)
- Masini, R. P., "Machine learning advances for time series forecasting", Journal of Economic Surveys, 37(1), pp.76~111 (2023)
- Matysiak, A., "The Great Recession and fertility in Europe : A sub-national analysis", European Journal of Population, 37(1), pp.29~64 (2021)
- Oh, Young-Eun, "An Exploratory Study on Changes in Perceptions of Marriage and Family Values in Korea", The Journal of Humanities and Social science, 11(1), pp.1217~1123 (2020)[DOI]
- Park, Mi-Kyung, "Priority Analysis and Policy Implications of Policies to Cope with Low Fertility : Policy Needs of MZ generation", The Journal of Korean Policy Studies, 22(1), pp.33~53 (2022)
- Sarker, I. H., "Machine learning: Algorithms, real-world applications and research directions", SN Computer Science, 2(3), pp.160~ (2021)
- Shin, Yoon-Jung, "Lessons from other countries on how to respond to low birthrates", National Assembly of the Republic of Korea, 687, pp.22~23 (2024)
- Sobotka, T., "Post-transitional fertility: The role of childbearing postponement in fuelling the shift to low and unstable fertility levels", Journal of Biosocial Science, 49(1), pp.S20~S45 (2017)
- Yoon, H., "Handbook of Aging, Health and Public Policy", pp.1~14 (2023)
- Yun, Jung-Ha, "Birth rate transition in the republic of Korea: Trends and Prospects", Journal of Korean Medical Science, 37(42), pp.e304~ (2022)