Details
| Originalsprache | Englisch |
|---|---|
| Aufsatznummer | 102063 |
| Fachzeitschrift | Journal of computational science |
| Jahrgang | 72 |
| Frühes Online-Datum | 2 Juni 2023 |
| Publikationsstatus | Veröffentlicht - Sept. 2023 |
Abstract
The identification of potential offenders, who are more likely to form a new group and co-offend in a crime, plays an essential role in narrowing down law enforcement investigations and improving predictive policing. Once a crime is committed, focusing on linking it to previously reported crimes and reducing the inspections based on shreds of evidence and the behavior of offenders can also greatly help law enforcement agencies. However, classical investigative techniques are generally case-specific and rely mainly on police officers manually combining information from different sources. Therefore, automatic methods designed to support co-offender research and crime linkage would be beneficial. This paper proposes two graph-based machine learning frameworks to address these issues based on a burglary use case, the first being transductive link prediction, which seeks to predict emergent links between existing graph nodes (which represent offenders or criminal cases), and the other being inductive link prediction, where connections are found between a new case and existing nodes. Our experimental results show a prediction accuracy of 68.5% in co-offender prediction, a 75.83% predictive accuracy for transductive crime linkage, and up to 74.8% accuracy in inductive crime linkage.
ASJC Scopus Sachgebiete
- Mathematik (insg.)
- Theoretische Informatik
- Informatik (insg.)
- Allgemeine Computerwissenschaft
- Mathematik (insg.)
- Modellierung und Simulation
Ziele für nachhaltige Entwicklung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Journal of computational science, Jahrgang 72, 102063, 09.2023.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Inductive and transductive link prediction for criminal network analysis
AU - Ahmadi, Zahra
AU - Nguyen, Hoang H.
AU - Zhang, Zijian
AU - Bozhkov, Dmytro
AU - Kudenko, Daniel
AU - Jofre, Maria
AU - Calderoni, Francesco
AU - Cohen, Noa
AU - Solewicz, Yosef
N1 - Funding Information: This work was supported by the European Union’s Horizon 2020 research and innovation program under grant agreement No. 833635 (project ROXANNE: Real-time network, text, and speaker analytics for combating organized crime, 2019-2022).
PY - 2023/9
Y1 - 2023/9
N2 - The identification of potential offenders, who are more likely to form a new group and co-offend in a crime, plays an essential role in narrowing down law enforcement investigations and improving predictive policing. Once a crime is committed, focusing on linking it to previously reported crimes and reducing the inspections based on shreds of evidence and the behavior of offenders can also greatly help law enforcement agencies. However, classical investigative techniques are generally case-specific and rely mainly on police officers manually combining information from different sources. Therefore, automatic methods designed to support co-offender research and crime linkage would be beneficial. This paper proposes two graph-based machine learning frameworks to address these issues based on a burglary use case, the first being transductive link prediction, which seeks to predict emergent links between existing graph nodes (which represent offenders or criminal cases), and the other being inductive link prediction, where connections are found between a new case and existing nodes. Our experimental results show a prediction accuracy of 68.5% in co-offender prediction, a 75.83% predictive accuracy for transductive crime linkage, and up to 74.8% accuracy in inductive crime linkage.
AB - The identification of potential offenders, who are more likely to form a new group and co-offend in a crime, plays an essential role in narrowing down law enforcement investigations and improving predictive policing. Once a crime is committed, focusing on linking it to previously reported crimes and reducing the inspections based on shreds of evidence and the behavior of offenders can also greatly help law enforcement agencies. However, classical investigative techniques are generally case-specific and rely mainly on police officers manually combining information from different sources. Therefore, automatic methods designed to support co-offender research and crime linkage would be beneficial. This paper proposes two graph-based machine learning frameworks to address these issues based on a burglary use case, the first being transductive link prediction, which seeks to predict emergent links between existing graph nodes (which represent offenders or criminal cases), and the other being inductive link prediction, where connections are found between a new case and existing nodes. Our experimental results show a prediction accuracy of 68.5% in co-offender prediction, a 75.83% predictive accuracy for transductive crime linkage, and up to 74.8% accuracy in inductive crime linkage.
KW - Co-offender prediction
KW - Crime linkage
KW - Deep neural networks
KW - Inductive link prediction
KW - Machine learning
KW - Repeat offenders
KW - Transductive link prediction
UR - http://www.scopus.com/inward/record.url?scp=85163757057&partnerID=8YFLogxK
U2 - 10.1016/j.jocs.2023.102063
DO - 10.1016/j.jocs.2023.102063
M3 - Article
AN - SCOPUS:85163757057
VL - 72
JO - Journal of computational science
JF - Journal of computational science
SN - 1877-7503
M1 - 102063
ER -