English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Anti-money laundering (AML) regulations play a critical role in safeguardingfinancial systems, but bear high costs for institutions and drive financialexclusion for those on the socioeconomic and international margins. The adventof cryptocurrency has introduced an intriguing paradox: pseudonymity allowscriminals to hide in plain sight, but open data gives more power toinvestigators and enables the crowdsourcing of forensic analysis. Meanwhileadvances in learning algorithms show great promise for the AML toolkit. In thisworkshop tutorial, we motivate the opportunity to reconcile the cause of safetywith that of financial inclusion. We contribute the Elliptic Data Set, a timeseries graph of over 200K Bitcoin transactions (nodes), 234K directed paymentflows (edges), and 166 node features, including ones based on non-public data;to our knowledge, this is the largest labelled transaction data set publiclyavailable in any cryptocurrency. We share results from a binary classificationtask predicting illicit transactions using variations of Logistic Regression(LR), Random Forest (RF), Multilayer Perceptrons (MLP), and Graph ConvolutionalNetworks (GCN), with GCN being of special interest as an emergent new methodfor capturing relational information. The results show the superiority ofRandom Forest (RF), but also invite algorithmic work to combine the respectivepowers of RF and graph methods. Lastly, we consider visualization for analysisand explainability, which is difficult given the size and dynamism ofreal-world transaction graphs, and we offer a simple prototype capable ofnavigating the graph and observing model performance on illicit activity overtime. With this tutorial and data set, we hope to a) invite feedback in supportof our ongoing inquiry, and b) inspire others to work on this societallyimportant challenge.

Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics