저출생 문제해결을 위한 한자녀 기혼여성의 후속 출산의향 예측: 머신러닝 방법의 적용

• 영문명: Predicting the Subsequent Childbirth Intention of Married Women with One Child to Solve the Low Birth Rate Problem in Korea: Application of a Machine Learning Method
• 발행기관: 한국보육지원학회
• 저자명: 전효정
• 간행물 정보: 『한국보육지원학회지』제20권 제2호, 127~143쪽, 전체 17쪽
• 주제분류: 사회과학 > 사회복지학
• 파일형태: PDF
• 발행일자: 2024.04.30

국문 초록

Objective: The purpose of this study is to develop a machine learning model to predict the subsequent childbirth intention of married women with one child, aiming to address the low birth rate problem in Korea, This will be achieved by utilizing data from the 2021 Family and Childbirth Survey conducted by the Korea Institute for Health and Social Affairs. Methods: A prediction model was developed using the Random Forest algorithm to predict the subsequent childbirth intention of married women with one child. This algorithm was chosen for its advantages in prediction and generalization, and its performance was evaluated. Results: The significance of variables influencing the Random Forest prediction model was confirmed. With the exception of the presence or absence of leave before and after childbirth, most variables contributed to predicting the intention to have subsequent childbirth. Notably, variables such as the mother's age, number of children planned at the time of marriage, average monthly household income, spouse's share of childcare burden, mother's weekday housework hours, and presence or absence of spouse's maternity leave emerged as relatively important predictors of subsequent childbirth intention.

목차

I. 서 론

Ⅱ. 연구방법

Ⅲ. 결과 및 해석

Ⅳ. 논의 및 결론

키워드

subsequent childbirth intention married women with one child low birth rate problem in Korea machine learning method