Can We Predict Child Abuse?

Is there a way to predict child abuse? We use similar technology in policing to predict areas of where crime will most likely occur. Florida was part of a study conducted by SAS Global who developed the innovative software. The study conclusion was delivered to the Florida Department of Children and Families in August 2016. According to Heimpel (2017), Chronicles of Social Change Organization reported the SAS report is one of the most extensive data examination done in Florida on child abuse reports, parents information, child data along with other data to produce a predictive analysis of possible recurring child abuse adults in the cases examined.

In this author’s experience, child abuse and neglect are generational. Many cases investigated showed 3rd, 4th and 5th generations of abuse and neglect within the families. We need to be proactive to stop the abuse.

Will Jones who is the company’s child wellbeing industry worked on the Florida study.  SAS reported in a slideshow “many of the highest risk perpetrators are young mothers with young children, a history of victimization, and a large number of networked reports in the past” (Heimpel, 2017, p.1).  Their intensive study examined a four-month-old baby who died from Sudden Infant Death Syndrome as a case example. Connecting the data revealed child abuse and neglect in the family for 10 years, ie generational abuse.

What SAS has developed is essentially similar put has the power to predict based on risk factors. We already know some factors identified from research that inform us the risks to children of that family for possible maltreatment. For example, some risk factors identified are young teen mothers, children of maltreatment who later become parents, families with multiple maltreatment reports, poverty, the age of the parent, visibility of the child are just a few risk factors. But, what SES is informing us the information we do not know gleaned from an in-depth analysis.

The firm found 42% of 291,499 adults in the study who had one prior child maltreatment report would have another report within 8 to 10 years. Approximately, 10% researchers identified as “chronic maltreatment group” with those in the group who had more than five maltreatment reports. This approach changes the focus to the adults and their behaviors and is an actuarial risk assessment (Heimpel, 2017).

Is using predictive analysis tools ethical when used with child welfare investigations? The determination of what happens with children in cases is the ultimate ethical concerns. If we remove a child from a home that should not have been removed or make mistakes on decisions of child safety that put a child at further risks or even death, then we have allowed technology to overcome human decision making in contrast to agency goals to keep children safe.

Heimpel, D. (2017, Jan 31). ‘Perpetrator’ Networks Key to Predicting Child Abuse. Chronicle of Social Change Organization. Retrieved from


4 thoughts on “Can We Predict Child Abuse?

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s