« All Events

Ethics in AI Seminar

Developing Spatial Predictive Risk Modeling for Child Maltreatment Early Intervention: Data Bias and Ethical Challenges

Child maltreatment has become a prevalent problem and draws increasing concern around the world. According to a recent study, approximately one in four children may experience child abuse or neglect in their lifetime. The impact of child maltreatment has also been linked to various long-term health concerns. The recent advances of machine learning and linked big data have motivated several efforts in developing new predictive risk models. Those models aim to predict at-risk populations to allow early intervention and prevention opportunities. In the US, such studies and exploration have been initiated by child protection services in several states. In this talk, we present an ongoing collaboration project developing a spatial risk model utilizing administrative data from different sources. Rather than focusing on the household and child level, the model divides a large region of interest into small spatial areal units and assesses risk levels at each areal unit. The assessment can help decision makers in child protection services generate insights and promote prevention actions at the community level. In the presentation, we will describe our progress and approaches. We especially want to discuss data bias and ethical challenges associated with building such predictive models.


Weijia Xu is the group lead for the Scalable Computational Intelligence group within the Texas Advanced Computing Center. His main research interest is in the field of large-scale information management and analysis.

Presented by the Institute for Foundations of Machine Learning and Good Systems. Learn more and register.

Dec 13, 2021
2:00 pm

See more below...