Machine learning partners in criminal networks

Abstract

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.

Modeling the role of police corruption in the reduction of organized crime: Mexico as a case study

“…Although previous models have analyzed organized crime using complex network tools [56][57][58][59][60][61] , to our knowledge, this is the first time in which a mathematical/computational agent based model of organized crime incorporates a feedback between the corruption (and its perception) of police corporations and the incidence of crime in a society. We do this by first introducing a fixed fraction F c of corrupt police officers who release a criminal if the bribe is high enough, and second by increasing the probability p m that a regular citizen becomes a criminal depending on the level of corruption, either real and/or perceived.…”

Fraud Detection and Anti-Money Laundering Applying Machine Learning Techniques in Cryptocurrency Transactional Graphs

“…It proved to be superior to other methods for detecting money laundering in a banking transaction dataset. Lopes et al (2022) also found node2vec effective in identifying criminal and non-criminal relationships in criminal networks when combined with predictive ML methods. The studies show that node2vec has the potential to be a valuable tool for analyzing financial and criminal transactions.…”

Extracting macroscopic quantities in crowd behaviour with deep learning

“…Over recent years, advancements in artificial intelligence (AI) have led to significant breakthroughs across scientific domains [19]. This development has enabled the collection of vast amounts of data and the application of cutting-edge machine learning(ML) techniques to social systems, e.g., criminal networks [20][21][22] and evacuation behaviours [23][24][25][26][27][28]. Deep learning (DL), a subset of ML, provides a unique tool to discern underlying patterns in intricate data.…”