Last Updated: 6/26/2017 3:35 PM
Predictive analytics promises to help child welfare agencies better understand which groups of children in their communities may have an increased chance of being in danger of abuse. However, there are several factors to consider. Child welfare caseworkers and supervisors regularly find themselves in situations as unique and distinctive as each member of the families they serve. Decisions are made daily about whether to initiate a case, file in court, remove a child from his or her home, or determine who is most connected to a child to help reduce trauma. In each of these instances, it’s important we develop tools that support and empower the social work professionals who find themselves on the frontlines constantly assessing information and trying to understand a child’s whole story to be able to make informed, confident decisions.
The Chronicle of Social Change provides an honest look at predictive analytics in child welfare through examples like L.A.’s Child Protection Hotline and Allegheny County, Pennsylvania. Having followed work by Emily Putnam-Hornstein for the past several years, the reference to “predictive risk” in this article resonated with me more than anything else. At the end of the day, predictive analytics promises to be a tool that can help identify what situations or set of variables cause certain children and families to potentially be most at risk. However, regardless of how much we advance our work with data and technology, machines alone can’t answer the entire need. Child welfare social work requires education, training, and observation, and skills like empathy, listening, and benevolence. Every child and family is different. It is my hope that we as social workers can feel informed by analytics, but also apply our caring, critical thinking skills to the data to engage children and families in a meaningful way.