Abstract

Violence risk assessment is an internationally recognised methodology, aimed to manage different forms of violence. Most risk assessment tools, as is the case of the reviewed one, are designed to protect victims in the context of pressure, little time, or little information. This paper presents a reply to Valdivia et al. (AI & Society, July 2024) criticism of the algorithm for intimate partner violence risk assessment—EPV—used in the Basque Country. They concluded that more than 50% of high-risk victims are in danger, using results from a pilot version of the instrument, not the reviewed one published in 2010, nor the system in use since May 2013. In addition, qualitative information from a single professional generates global criticisms of the tool. Neither the current cut-off points nor the real weighting of the items nor the real risk management procedure are considered, and the personal opinion of a judge is assumed to be better than the use of tools when the accumulated research shows the opposite. When EPV risk assessment reports are used in courts, they may only temporarily affect some perpetrator rights, imposing restraining orders or, in the worst case, pretrial prison waiting for sentence. However, risk management can save the life of the victim. Cautions and suggestions related to the judicial context, such as improving risk reports or training judicial professionals, are shared. However, Valdivia et al.’s paper leads to misconceptions that extend to different sectors when echoing the wrong conclusions of their paper.