The paper discusses the creation of two datasets for studying the predictability of fertility outcomes in the Netherlands. One dataset is based on the LISS panel, a longitudinal survey with thousands of variables on various topics, including individual preferences and values. The other dataset is based on Dutch register data, which has detailed information about the life courses of millions of Dutch residents but lacks attitudinal data. These datasets form the basis of the PreFer fertility prediction data challenge starting in Spring 2024. The paper argues that measuring the predictability of fertility outcomes using these datasets can advance our understanding of fertility behaviour and computational social science.
Publication date: 2 Feb 2024
Project Page: Unavailable
Paper: https://arxiv.org/pdf/2402.00705
