Economic crimes including corruption, fraud, collusion, and tax evasion impose significant costs to societies all around the world. These crimes are carried out by groups with sophisticated organizational patterns, and leave complex traces in data. The application of network methods to study the structure and dynamics of economic crime have made significant advances in recent years.
In this satellite, we gather leading researchers applying the methods and theories of network science and social network analysis to the problems and challenges of economic crime. Our aims are to survey recent advances and to encourage the cross-pollination of ideas between disciplines.
Preliminary Program: June 29th (all times EST)
8:30 - Opening Remarks
8:40 - Keynote 1: Isabella Gollini
A latent space approach for modelling interactions among offenders.
Police data offer an increasingly exploited source of evidence whose secondary nature poses challenges for researchers. A key issue is that researchers often have to deal with two sets of actors: targeted and non-targeted. This work develops a latent space model for interdependent ego-networks so as to deal with the targeted nature of police evidence. By treating targeted offenders as egos and their contacts as alters, the model is presented to investigate the latent structure of criminal networks. This allows us to explain the relational structure of the data by estimating the positions of the offenders in a latent social space. In particular, we illustrate this new methodology by exploring a complex network consisting of interdependent ego-networks based on the wiretaps acquired by the Italian Police in 2014 on 28 targeted offenders (egos) during an investigation about human smuggling out of Libya. The statistical challenge with these ego-networks is that the large number of alters (more than 15k) can potentially be members of several ego-networks. Moreover, from a computational point of view, this model is difficult to estimate due to the intractability of the likelihood. To efficiently overcome this difficulty we adopt an efficient variational algorithm. The flexible modelling framework introduced can be adapted to a wide range of network settings.
9:20 - Keynote 2: Scott Duxbury
Shining a light on the shadows: Endogenous trade networks and the growth of an online illegal market.
Although markets rely on governmental oversight to enforce contracts and guarantee cooperation in exchange, little research has considered how illegal markets, which evade and work against the state, grow and develop. Using unique transaction-level data on 7,196 market actors and 16,847 illegal drug exchanges on a “darknet” drug market, this study evaluates the network processes that shape online illegal drug trade and promote the growth of online illegal drug markets. While past research on online markets has found that networks have little influence on trade relationships due to market actors’ relative anonymity and because repeated transactions are rare, we argue that the high-risk context of illegal trade enhances market actors’ reliance on social relationships that emerge endogenously from transaction networks. Consistent with this explanation, findings reveal a highly structured trade network characterized by dense clustering and frequent recurrent drug exchange. Dynamic network models reveal that embeddedness and closure in exchange structure both increase the hazard rate of illegal drug trade with effect sizes comparable to formal reputations. These effects are pronounced in the early stages of market development, where risk is greatest. However, they become negative or insignificant once the market reaches maturity, where reputations are well-established. These findings demonstrate the powerful yet temporally contingent influence of transaction networks on illegal trade in online markets and reveal how endogenous networks of economic relations can promote risky exchange under conditions of relative anonymity and illegality.
10:00 - Break
10:15 - Keynote 3: Mark Weber
Graph Convolutional Networks for Anti-Money Laundering
While deep learning has done remarkable things on Euclidean data (e.g. audio, images, video) graph deep learning has lagged because combinatorial complexity and nonlinearity issues making training very difficult and expensive. Yet it’s precisely the information hidden in that complexity that makes graphs so interesting. In this talk, Mark Weber will introduce a class of methods known as scalable graph convolutional networks (GCN) and share published experimental results from a semi-supervised anomaly detection task in financial forensics and anti-money laundering in Bitcoin.
10:55 - Keynote 4: Issa Luna Pla & José R. Nicolás-Carlock
Corporate networks in public procurement corruption scandals
Governments lose significant funds due to corruption in public procurement. While most efforts have focused on strategies to tackle fraud schemes at all stages of the contracting process, there are fewer analyses related to the corporate features of companies involved in procurement that would be most likely to signal organized criminal activities. In this talk, we explore four important and recent documented cases of local and federal corruption in public procurement in Mexico, where hundreds of regular and irregular companies were used to embezzle billions of dollars. In terms of criminal conspiracy, we discuss how the network analysis of companies at the ownership and management level reveals important collective behaviors that need to be considered in the design of procurement risk assessment frameworks.
11:35 - Break
11:50 - Accepted Contributions:
Networks of tax evasion in Mexico. Martin Zumaya, Martha Gómez, Nephtalí Garrido, Carlos Gershenson, Gerardo Iñiguez, Carlos Pineda
Paths between economic and violent crimes: a network perspective. Georg Heiler, Jan Korbel, Tuan Pham, Stefan Thurner
12:25 - Closing Remarks
Invitation to contribute
The satellite will have space for contributed talks of 10/15-minute presentations. Participants are invited to submit an abstract in PDF format.
>>>Link to submission site<<<
Topics of interest include but are not limited to:
- Tax Evasion and Money Laundering
- Trafficking Networks
- Missing link prediction and mathematical models for inferring network structure
- Detecting fraud in transaction networks
- Mafia and OC networks
- Social and communication networks of criminal groups
- Political corruption networks
-Lobbying and influence networks and corruption in public administration
- Analysis of procurement networks
Submissions should be at most 2 pages long (figure included) and should include: title, author(s), affiliation(s), and e-mail address(es). Submissions will be evaluated and selected by the organizers, based on fit to the theme of the satellite, originality, and soundness.
Deadline for submissions: June 1.
Acceptance notifications will be sent by June 10.
EPJ Data Science Special Issue
Contributors and attendees may be interested in the call for contributions for an upcoming issue of EPJ Data Science on the same topic as the satellite.