Criminal networks analysis in missing data scenarios through graph distances

Abstract

Data collected in criminal investigations may suffer from issues like: (i) incompleteness, due to the covert nature of criminal organizations; (ii) incorrectness, caused by either unintentional data collection errors or intentional deception by criminals; (iii) inconsistency, when the same information is collected into law enforcement databases multiple times, or in different formats. In this paper we analyze nine real criminal networks of different nature (i.e., Mafia networks, criminal street gangs and terrorist organizations) in order to quantify the impact of incomplete data, and to determine which network type is most affected by it. The networks are firstly pruned using two specific methods: (i) random edge removal, simulating the scenario in which the Law Enforcement Agencies fail to intercept some calls, or to spot sporadic meetings among suspects; (ii) node removal, modeling the situation in which some suspects cannot be intercepted or investigated. Finally we compute spectral distances (i.e., Adjacency, Laplacian and normalized Laplacian Spectral Distances) and matrix distances (i.e., Root Euclidean Distance) between the complete and pruned networks, which we compare using statistical analysis. Our investigation identifies two main features: first, the overall understanding of the criminal networks remains high even with incomplete data on criminal interactions (i.e., when 10% of edges are removed); second, removing even a small fraction of suspects not investigated (i.e., 2% of nodes are removed) may lead to significant misinterpretation of the overall network.

A Systematic Review of Mobile Phone Data in Crime Applications: A Coherent Taxonomy Based on Data Types and Analysis Perspectives, Challenges, and Future Research Directions

“…Cavallaro et al [91] reconstructed the criminal network of the Sicilian Mafia by applying SNA tools and matrices to identify key leaders and their reports, such as bosses and intermediaries. Ficara et al [94] built a network of suspected criminals based on their calling information; here, the nodes were represented by suspected members and the edges were represented by phone call records. Dileep et al [95] similarly proposed a forensic detection system to detect the development of suspicious communities based on extracted phone call records.…”

Human and Social Capital Strategies for Mafia Network Disruption

“…Our analysis focuses on two real criminal networks related to a specific anti-mafia operation called Montagna [4]- [6], [8]- [10].…”

“…Herein, we borrow methods and tools from Social Network Analysis (SNA) to investigate the effectiveness of several law enforcement interventions against two Mafia networks, based on a real-world dataset built from a major anti-mafia operation called "Montagna" which was concluded in 2007. This dataset was used in different studies on Mafia networks through SNA to analyze the structure of such networks [3], [4], identify subgroups and highlight actors in strategic positions [5]- [7], and develop disruption and prevention methods [8]- [10].…”

Forecasting the Missing Links in Heterogeneous Social Networks

“…Criminal networks are described as a group operational beyond the limitations of the law and making a profit using an unlawful manner which is generally gained by detriment to other individuals or organizations [3]. Due to this reason, researchers and scholars are significantly adapting to social network analysis to investigate the criminal trend, as it is a potent tool to analyze criminal networks and get richer insight into their behaviour.…”