20.500.12556/DKUM-88735-334e8c84-84aa-3395-f9a3-555832947098 Machine learning partners in criminal networks 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 diferent 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 signifcant 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. machine learning crime network social physics strojno učenje kriminal omrežje fizika družbe true true true Nature Publishing Group Angleški jezik Slovenski jezik Znanstveno delo 2024-05-22 03:33:21 2024-05-28 14:43:03 2024-07-16 03:58:08 0000-00-00 00:00:00 2022 0 0 Str. 1-9 Št. članka 15746 Letn. 12 2022 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2022-05-03 2022-09-07 2022-09-21 53 123688707 10.1038/s41598-022-20025-w 2045-2322 Lopes-2022-Machine_learning_partners_in_crimin.pdf Lopes-2022-Machine_learning_partners_in_crimin.pdf 1 A043AB12AAE0819F8D1D5C4A09A12EA8 eb220df8700dc381879a3ba20a0aec496ba04dffd1ea8f40ec8e4497c9f7be97 854d588d-429d-11ef-99b3-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=181482 https://doi.org/10.1038/s41598-022-20025-w 0 95b8a7da-429d-11ef-99b3-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=181483 Fakulteta za naravoslovje in matematiko 0 0 0