A Different Way of Doing Things: Big Data is Coming for Child Welfare

We’re Robert and Kathey Raskin, and if this is your first time here, then you’re probably intrigued about what we are trying to do here. We try to write daily, so come back in the next few days for a fresh post. Now, we’re continually talking about the overhaul of the child welfare system across the United States. There’s systemic abuse of the order by its workers, the people utilizing the service, and local governments. It needs a complete and total overhaul. A lot of the methods can be part of the 21st century by embracing the resources provided by the so-called big data niche of tech.

But First, the Facts

Roughly 7 million children come to the attention of child welfare authorities every year in the United States; one in three will be the subject of maltreatment investigations in their lifetimes. This data is what we shed light on every time we hear about another new case. Emily Putnam-Hornstein – a USC professor of social work – thought that there had to be a better way to protect kids. Frequently there are fraudulent or non-emergency issues submitted to the child welfare system.

She noted that the system has lots of calls of potential abuse and neglect, but the investigators find it was a misunderstanding. We are wasting resources that could be on the kids who get lost in the system. Since we don’t have the people power to sift through the noise, she hit on the way to identify and protect children more efficiently.

Pennsylvania is Onboard

Allegheny County, Pennsylvania connected with Putnam-Hornstein to develop a predictive analytics tool for the Office of Children, Youth and Families to help screen allegations of child abuse and neglect. That Pittsburgh-based agency is under scrutiny for failing to investigate kids who died from maltreatment.

Thousands of child maltreatment referrals were studied to help create an algorithm that would assign a “risk” score to every family reported to Allegheny County child protective services. The process eliminates the biases and randomness of human decision-making. The algorithm considers a handful of factors and computes the family’s risk based on dozens of determinants from public databases: use of mental health and drug treatment services, criminal histories, receipt of government benefits, and so on. The human screeners get a say, and there are checks and balances to make sure nothing falls through the cracks.

American Enterprise Institute has further insight into how big data could work to revolutionize the dated system in place and to help remove the corruption that exists that we’ve reported on for so long.


Leave a Reply

Your email address will not be published. Required fields are marked *