CHICAGO — The Illinois Department of Children and Family Services will end a $366,000 program that uses computer data mining to identify children at risk for serious injury or death after the agency's director called the technology unreliable.
DCFS Director Beverly Walker told the Chicago Tribune that the agency is suspending use of the Rapid Safety Feedback program because it "didn't seem to be predicting much."
The department is now seeking to change the way it indexes and links investigations. It's also considering legislative changes that would allow the department to retain records of past unproven allegations.
"Predictive analytics (wasn't) predicting any of the bad cases," Walker said. "I've decided not to proceed with that contract."
The department's decision comes after the predictive analytics program failed to flag high-risk cases of children that in some instances resulted in deaths.
The newspaper said that in two of those cases it found the automated system was riddled with data entry errors. According to the Tribune, the program also didn't link investigations about many children to cases regarding their siblings, or other adults in the same home.
The nonprofit Eckerd Connects, which created the analytics program, said it regrets using language that suggested the company could predict the probability of child harm.
"We all agree that we could have done a better job with that language. I admit it is confusing," said Eckerd spokesman Douglas Tobin.
Eckerd and its for-profit partner, Mindshare Technology, mined electronic DCFS files and assigned a score of 1 to 100 to children who were the subject of an abuse allegation. The algorithms rated the children's risk of being killed or severely injured.
Eckerd said its scoring system is merely meant to represent how closely a child matches historical data on fatality and harm cases.