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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Blockchain provides the unique and accountable channel for financialforensics by mining its open and immutable transaction data. A recent surge hasbeen witnessed by training machine learning models with cryptocurrencytransaction data for anomaly detection, such as money laundering and otherfraudulent activities. This paper presents a holistic applied data scienceapproach to fraud detection in the Bitcoin network with two originalcontributions. First, we contribute the Elliptic++ dataset, which extends theElliptic transaction dataset to include over 822k Bitcoin wallet addresses(nodes), each with 56 features, and 1.27M temporal interactions. This enablesboth the detection of fraudulent transactions and the detection of illicitaddresses (actors) in the Bitcoin network by leveraging four types of graphdata: (i) the transaction-to-transaction graph, representing the money flow inthe Bitcoin network, (ii) the address-to-address interaction graph, capturingthe types of transaction flows between Bitcoin addresses, (iii) theaddress-transaction graph, representing the bi-directional money flow betweenaddresses and transactions (BTC flow from input address to one or moretransactions and BTC flow from a transaction to one or more output addresses),and (iv) the user entity graph, capturing clusters of Bitcoin addressesrepresenting unique Bitcoin users. Second, we perform fraud detection tasks onall four graphs by using diverse machine learning algorithms. We show thatadding enhanced features from the address-to-address and theaddress-transaction graphs not only assists in effectively detecting bothillicit transactions and illicit addresses, but also assists in gainingin-depth understanding of the root cause of money laundering vulnerabilities incryptocurrency transactions and the strategies for fraud detection andprevention. Released at github.com/git-disl/EllipticPlusPlus.

Demystifying Fraudulent Transactions and Illicit Nodes in the Bitcoin Network for Financial Forensics