# Prison data analysis finds choosing lowest reoffending risk scores preserves overall accuracy > HelixNews · Web page: https://helixnews.one/story/294140 · All pages for agents: https://helixnews.one/llms.txt 1 outlet covering · First listed: Phys.org, Nov 10, 2026, 5:00 PM · Read it: Whether an individual reoffends after their release from prison or is successfully rehabilitated depends on several factors. When assessing the risk of recidivism, all of these are taken into account—both by human experts and by machine learning models. If several equally reliable computational models produce different risk ratings, the lowest value should be used for the individual concerned, suggest Ashwin Singh (TU Wien) and Carlos Castillo (ICREA/Universitat Pompeu Fabra). ## Who's covering it In the order they published: - Nov 10, 2026, 5:00 PM: [Prison data analysis finds choosing lowest reoffending risk scores preserves overall accuracy]() — Phys.org (Science news) Whether an individual reoffends after their release from prison or is successfully rehabilitated depends on several factors. When assessing the risk of recidivism, all of these are taken into account—both by human experts and by machine learning models. If several equally reliable computational models produce different risk ratings, the lowest value should be used for the individual concerned, suggest Ashwin Singh (TU Wien) and Carlos Castillo (ICREA/Universitat Pompeu Fabra).