Machine learning partners in criminal networks.

Autor: Lopes DD; Departamento de Física, Universidade Estadual de Maringá, Maringá, PR, 87020-900, Brazil., Cunha BRD; Rio Grande do Sul Superintendency, Brazilian Federal Police, Porto Alegre, RS, 90160-093, Brazil.; National Police Academy, Brazilian Federal Police, Brasília, DF, 71559-900, Brazil., Martins AF; Departamento de Física, Universidade Estadual de Maringá, Maringá, PR, 87020-900, Brazil., Gonçalves S; Instituto de Física, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, 91501-970, Brazil., Lenzi EK; Departamento de Física, Universidade Estadual de Ponta Grossa, Ponta Grossa, PR, 84030-900, Brazil., Hanley QS; School of Science and Technology, Nottingham Trent University, Clifton Lane, Nottingham, NG11 8NS, UK., Perc M; Faculty of Natural Sciences and Mathematics, University of Maribor, Koroška cesta 160, 2000, Maribor, Slovenia. matjaz.perc@gmail.com.; Department of Medical Research, China Medical University Hospital, China Medical University, Taichung, Taiwan. matjaz.perc@gmail.com.; Alma Mater Europaea, Slovenska ulica 17, 2000, Maribor, Slovenia. matjaz.perc@gmail.com.; Complexity Science Hub Vienna, Josefstädterstraße 39, 1080, Vienna, Austria. matjaz.perc@gmail.com., Ribeiro HV; Departamento de Física, Universidade Estadual de Maringá, Maringá, PR, 87020-900, Brazil. hvr@dfi.uem.br.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2022 Sep 21; Vol. 12 (1), pp. 15746. Date of Electronic Publication: 2022 Sep 21.
DOI: 10.1038/s41598-022-20025-w
Abstrakt: Recent research has shown that criminal networks have complex organizational structures, but whether this can be used to predict static and dynamic properties of criminal networks remains little explored. Here, by combining graph representation learning and machine learning methods, we show that structural properties of political corruption, police intelligence, and money laundering networks can be used to recover missing criminal partnerships, distinguish among different types of criminal and legal associations, as well as predict the total amount of money exchanged among criminal agents, all with outstanding accuracy. We also show that our approach can anticipate future criminal associations during the dynamic growth of corruption networks with significant accuracy. Thus, similar to evidence found at crime scenes, we conclude that structural patterns of criminal networks carry crucial information about illegal activities, which allows machine learning methods to predict missing information and even anticipate future criminal behavior.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje