IBM / AMLSim

The AMLSim project is intended to provide a multi-agent based simulator that generates synthetic banking transaction data together with a set of known money laundering patterns - mainly for the purpose of testing machine learning models and graph algorithms. We welcome you to enhance this effort since the data set related to money laundering is critical to advance detection capabilities of money laundering activities.
Apache License 2.0
251 stars 81 forks source link

Iss 43 - Pick a rounded amount for AML Fan In and Fan Out Transactions #49

Closed nelsonjd closed 2 years ago

nelsonjd commented 2 years ago

According to the Wiki the AML typologies for fan out and fan in should be rounded amounts. I'm starting with a scheme that rounds them to large amounts that lead to possibilities of about 7 to 30 between the min and max. So a min of 3000, and max. of. 4000 would result in random amounts of 3100, 3200, 3300, 3400 etc.

@hkanezashi @suzumura

nelsonjd commented 2 years ago

This pr addresses this issue https://github.com/IBM/AMLSim/issues/43. It keeps them all the same amount, though, according to the wiki, but rounds them like the wiki says.