A new study has found that using data analysis and computer learning at an arraignment to analyze the chances of a repeat domestic violence incident reduced new cases by half, leading to more than 1,000 fewer arrests annually in one large metropolitan area.
After an arrest, the first court appearance is usually the preliminary arraignment, when a judge or magistrate decides whether to release the suspect or hold them in jail, based on the likelihood the person will return to court or commit new crimes.
Arraignments are usually very short, with decisions based on limited data. However, Drs. Richard Berk and Susan B. Sorenson of the University of Pennsyvania found that using computer forecasts at these proceedings can dramatically reduce subsequent domestic violence arrests.
“A large number of criminal justice decisions by law require projections of the risk to society. These threats are called ‘future dangerousness,'” said Berk, a criminology and statistics professor at Penn’s School of Arts & Sciences and Wharton School.
“Many decisions, like arraignments, are kind of seat of the pants. The question is whether we can do better than that, and the answer is yes we can. It’s a very low bar.”
For domestic violence crimes between intimate partners, parents, and children, or even siblings, there’s typically a threat to one particular person, said Sorenson, a professor of social policy in Pennsylvania’s School of Social Policy & Practice who also directs the Evelyn Jacobs Ortner Center on Family Violence.
“It’s not a general public safety issue,” she said. “With a domestic violence charge, let’s say a guy — and it usually is a guy — is arrested for this and is awaiting trial. He’s not going to go assault some random woman. The risk is for a re-assault of the same victim.”
To understand how computer learning could help in domestic violence cases, Berk and Sorenson obtained data from more than 28,000 domestic violence arraignments between January 2007 and October 2011. They also looked at a two-year follow-up period after release that ended in October 2013.
A computer can “learn” which kinds of individuals are likely to re-offend, according to the scientists. For this research, the 35 initial inputs included age, gender, prior warrants and sentences, and residential location.
These data points help the computer understand appropriate associations for projected risk, offering extra information to a court official deciding whether to release an offender.
“In all kinds of settings, having the computer figure this out is better than having us figure it out,” Berk said.
That’s not to say there aren’t obstacles to its use, he noted.
The number of mistaken predictions can be unacceptably high, and some people object in principle to using data and computers in this manner. To both of these points, the researchers respond that using the computer — what they call machine learning — is simply a tool.
“It doesn’t make the decisions for people by any stretch,” Sorenson said. These choices “might be informed by the wisdom that accrues over years of experience, but it’s also wisdom that has accrued only in that courtroom. Machine learning goes beyond one courtroom to a wider community.”
In some criminal justice settings, use of machine learning is already routine, although different kinds of decisions require different datasets from which the computer must learn, the researchers noted. The underlying statistical techniques, however, remain the same, they added.
The Pennsylvania researchers believe machines learning can improve current practices.
“The algorithms are not perfect. They have flaws, but there are increasing data to show that they have fewer flaws than existing ways we make these decisions,” Berk said.
“You can criticize them — and you should because we can always make them better — but, as we say, you can’t let the perfect be the enemy of the good.”
The study was published in The Journal of Empirical Legal Studies.