A rule-based model for victim prediction. (December 2020)

• Record Type: Journal Article
• Authors: Ozer, Murat; Elsayed, Nelly; Varlioglu, Said; Li, Chengcheng; Ekici, Niyazi
• Is Part Of: International journal of law, crime and justice. Volume 63(2020)
• Publication Date: 2020-12
• Subjects: Rule-based system -- Network graph analysis -- Violent victimization -- Victim prediction; Law -- Periodicals; Criminology -- Periodicals; Justice -- Periodicals; Justice pénale -- Administration -- Périodiques; Criminologie -- Périodiques; Sociologie juridique -- Périodiques; Electronic journals; 340.11
• DOI: 10.1016/j.ijlcj.2020.100440
• Languages: English
• ISSNs: 1756-0616

Abstract

Abstract: The present study proposes a novel automated model, called Vulnerability Index for Population at Risk (VIPAR) scores, to identify rare populations for their future shooting victimizations. Likewise, the focused deterrence approach identifies vulnerable individuals and offers certain treatments (e.g., outreach services) to prevent violence in communities. Our rule-based engine model is the first AI-based model for victim prediction purposes. The model merit is the usage of criminology studies to construct the rule-based engine to predict victims. This paper aims to compare the list of focused deterrence strategy with the VIPAR score list regarding their predictive power for the future shooting victimizations. Drawing on the criminological studies, this study uses age, past criminal history, and peer influence as the main predictors of future violence. Network graph analysis is employed to measure the influence of peers on the outcome variable. The proposed model also uses logistic regression analysis to verify the variable selections in the model. Following the analytical process, the current research creates an automated model (VIPAR scores) to predict vulnerable populations for their future shooting involvements. Our empirical results show that VIPAR scores predict 25.8% of future shooting victims and 32.2% of future shooting suspects, whereas the focused deterrence list predicts 13% of future shooting victims and 9.4% of future shooting suspects. The proposed model outperforms the intelligence list of focused deterrence policies in predicting the future fatal and non-fatal shootings. Furthermore, this paper discusses the concerns about the presumption of innocence right. Highlights: Predicting a shooting attack victim using a rule-based system that established on criminology theory. The first artificial intelligent-based victim prediction model. The prediction results outperforms the existing stat-of-the-art victim prediction models.