We compare predictions from a conventional protocol-based approach to risk assessment with those based on a machine-learning approach. We first show that the conventional predictions are less accurate than, and have similar rates of negative prediction error as, a simple Bayes classifier that...

We compare predictions from a conventional protocol-based approach to risk assessment with those based on a machine-learning approach. We first show that the conventional predictions are less accurate than, and have similar rates of negative prediction error as, a simple Bayes classifier that...

Domestic abuse is a pervasive global problem. Here we analyze two approaches to reducing violent DA recidivism. One involves charging the perpetrator with a crime; the other provides protective services to the victim on the basis of a formal risk assessment carried out by the police. We use...

Domestic abuse is a pervasive global problem. Here we analyze two approaches to reducing violent DA recidivism. One involves charging the perpetrator with a crime; the other provides protective services to the victim on the basis of a formal risk assessment carried out by the police. We use...