Predicting Domestic Abuse (Fairly) and Police Risk Assessment
Fuente:
Redalyc
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Artículo científico |
| Langue: | en |
| Publié: |
Colegio Oficial de Psicólogos de Madrid
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1876431073290747904 |
|---|---|
| author | Emily Turner |
| author_facet | Emily Turner |
| contents | Predicting Domestic Abuse (Fairly) and Police Risk Assessment Emily Turner Gavin Brown Juanjo Medina-Ariza Psicología Policía Violencia doméstica Justicia algorítmica Evaluación de riesgos Aprendizaje automático Domestic abuse victim risk assessment is crucial for providing victims with the correct level of support. However, it has been shown that the approach currently taken by most UK police forces, the Domestic Abuse, Stalking, and Honour Based Violence (DASH) risk assessment, is not identifying the most vulnerable victims. Instead, we tested several machine learning algorithms and propose a predictive model, using logistic regression with elastic net as the best performing, that incorporates information readily available in police databases, and census-area-level statistics. We used data from a large UK police force including 350,000 domestic abuse incidents. Our models made significant improvement upon the predictive capacity of DASH, both for intimate partner violence (IPV; AUC = .748) and other forms of domestic abuse (non-IPV; AUC = .763). The most influential variables in the model were of the categories criminal history and domestic abuse history, particularly time since the last incident. We show that the DASH questions contributed almost nothing to the predictive performance. We also provide an overview of model fairness performance for ethnic and socioeconomic subgroups of the data sample. Although there were disparities between ethnic and demographic subgroups, everyone benefited from the increased accuracy of model-based predictions when compared with officer risk predictions. 2022 artículo científico 1132-0559 https://www.redalyc.org/articulo.oa?id=179873952002 https://www.redalyc.org/journal/1798/179873952002/ https://www.redalyc.org/journal/1798/179873952002/html/ https://www.redalyc.org/journal/1798/179873952002/179873952002.epub https://www.redalyc.org/journal/1798/179873952002/movil 10.5093/pi2022a11 en http://www.redalyc.org/revista.oa?id=1798 Psychosocial Intervention application/pdf Colegio Oficial de Psicólogos de Madrid Psychosocial Intervention (España) Num.3 Vol.31 |
| format | Artículo científico |
| id | redalyc_179873952002 |
| institution | Redalyc |
| language | en |
| publishDate | 2022 |
| publisher | Colegio Oficial de Psicólogos de Madrid |
| spellingShingle | Predicting Domestic Abuse (Fairly) and Police Risk Assessment Emily Turner Psicología Policía Violencia doméstica Justicia algorítmica Evaluación de riesgos Aprendizaje automático Predicting Domestic Abuse (Fairly) and Police Risk Assessment Emily Turner Gavin Brown Juanjo Medina-Ariza Psicología Policía Violencia doméstica Justicia algorítmica Evaluación de riesgos Aprendizaje automático Domestic abuse victim risk assessment is crucial for providing victims with the correct level of support. However, it has been shown that the approach currently taken by most UK police forces, the Domestic Abuse, Stalking, and Honour Based Violence (DASH) risk assessment, is not identifying the most vulnerable victims. Instead, we tested several machine learning algorithms and propose a predictive model, using logistic regression with elastic net as the best performing, that incorporates information readily available in police databases, and census-area-level statistics. We used data from a large UK police force including 350,000 domestic abuse incidents. Our models made significant improvement upon the predictive capacity of DASH, both for intimate partner violence (IPV; AUC = .748) and other forms of domestic abuse (non-IPV; AUC = .763). The most influential variables in the model were of the categories criminal history and domestic abuse history, particularly time since the last incident. We show that the DASH questions contributed almost nothing to the predictive performance. We also provide an overview of model fairness performance for ethnic and socioeconomic subgroups of the data sample. Although there were disparities between ethnic and demographic subgroups, everyone benefited from the increased accuracy of model-based predictions when compared with officer risk predictions. 2022 artículo científico 1132-0559 https://www.redalyc.org/articulo.oa?id=179873952002 https://www.redalyc.org/journal/1798/179873952002/ https://www.redalyc.org/journal/1798/179873952002/html/ https://www.redalyc.org/journal/1798/179873952002/179873952002.epub https://www.redalyc.org/journal/1798/179873952002/movil 10.5093/pi2022a11 en http://www.redalyc.org/revista.oa?id=1798 Psychosocial Intervention application/pdf Colegio Oficial de Psicólogos de Madrid Psychosocial Intervention (España) Num.3 Vol.31 |
| title | Predicting Domestic Abuse (Fairly) and Police Risk Assessment |
| topic | Psicología Policía Violencia doméstica Justicia algorítmica Evaluación de riesgos Aprendizaje automático |
| url | https://www.redalyc.org/articulo.oa?id=179873952002 https://www.redalyc.org/journal/1798/179873952002/ https://www.redalyc.org/journal/1798/179873952002/html/ https://www.redalyc.org/journal/1798/179873952002/179873952002.epub https://www.redalyc.org/journal/1798/179873952002/movil |