Fraud through the eyes of a machine

 By Medium - 2020-11-22

Description

Identifying suspicious connections via network analysis

Summary

  • Identifying suspicious connections via network analysis tl;dr Networks are built by matching transactions using shared attributes’ values.
  • In the world of online payments the nodes can be either transactions or specific values of transactions’ attributes.
  • Once the graph is created we can query it for various properties.
  • We can distinguish between normal traffic and carding patterns (few people, numerous cards and transactions) easily when having data structured as a network.

 

Topics

  1. Machine_Learning (0.37)
  2. Backend (0.21)
  3. Database (0.15)

Similar Articles

What was the data approach to breaking The FinCEN Files?

By diginomica - 2020-09-24

How do you work backwards from thousands of disconnected PDFs to the 100,000 suspicious financial transactions they’re reporting on? A combination of hard human work, OCR, data analysis and graph.

7 Ways Your Data Is Telling You It’s a Graph

By Neo4j Graph Database Platform - 2015-12-23

Watch (or read) Senior Project Manager Karen Lopez’s GraphConnect presentation on the signs that your data is actually a graph and needs a graph database.

Machine Learning in Fintech - Demystified

By datasciencecentral - 2020-11-24

Abstract – Big data helps to make strategy for future and understand user behaviors. In 1959, Arther Samuel gave very simple definition of Machine Learning as…