家庭托育需求测度及其影响因素研究——基于自动机器学习算法

Family Child Care Demand Measure and its Influencing Factors——Based on Automated Machine Learning

少子化、老龄化形势严峻,客观上要求以需求为导向推动托育服务有效供给,促进中国人口长期均衡发展。文章借助江苏省徐州市1601个家庭的调查数据,运用自动机器学习算法测度托育需求,结果显示:每千人口所需的托位数为4.8个;家庭特征显著影响托育需求,母亲年龄与月收入水平是最重要的影响因素,父亲受教育程度、隔代照顾次之;家庭对托育服务的认可度也显著影响托育需求。根据托育需求影响因素的重要性排序,可以构建以母亲的机会成本为逻辑起点的婴幼儿照顾方式决策过程。基于此,政策制订应在动态把握托育需求的基础上:一方面,明确政府责任,并充分调动社会力量参与服务供给,以提高托育服务供给总量;另一方面,应通过强化人才队伍建设,引入激励机制,以提高托育服务供给质量。

The severe situation of the aging population with lower fertility objectively requires the promotion of an effective supply of demand-oriented childcare services to facilitate the long-term balanced development of China's population.Using data from a survey of 1601 households in Xuzhou City,Jiangsu Province,Automated Machine Learning is used to measure the demand for childcare services.The results showed as follow:the number of childcare spaces required per 1,000 population is 4.8;family characteristics significantly influence the demand for childcare services,with the mother's age and income level being the most important influencing factors,followed by the father's education level and intergenerational care;family recognition of childcare services also influences demand for childcare services.Based on the ranking of the importance of the characteristics that influence the demand for childcare services,the decision-making process of infant care can be constructed with the opportunity cost of the mother as the logical starting point.Therefore,policy formulation should be based on a dynamic grasp of the demand for childcare.On the one hand,to clarify the government's responsibility and fully mobilize social forces to participate in service supply so as to improve the total supply of childcare services;On the other hand,the quality of childcare service supply should be improved by strengthening the construction of talent teams and introducing incentive mechanisms.