Ranking the Importance Level of Intermediaries to a Criminal using a Reliance Measure

摘要: Recent research on finding important intermediate nodes in a network suspected to contain criminal activity is highly dependent centrality values. Betweenness centrality, for example, widely used rank the that act as brokers shortest paths connecting all source and end network. However both path node betweenness linearly scaled can only show rankings In this paper we explore mathematical concept of pair-dependency nodes, adapting relationships introducing new source-intermediate reliance measure. To illustrate our measure, apply it Enron email dataset Noordin Top Terrorist networks. We compare ranking with Google PageRank, Markov well investigation using will lead different prioritisation terms possible people investigate. While terrorist yields more extreme differences than transaction network, latter values set finance managers immediately identified another employee convicted money laundering.