This project aims at building a multi-agent simulator of anti-money laundering - namely AML, and sharing synthetically generated data so that researchers can design and implement their new algorithms over the unified data.

All that is needed to run this is by running the shell script pipline.sh from the AMLSim directory

sh pipline.sh

Download the docker file within the repo (named Dockerfile), then run this command within that directroy

docker build -t amlsim --build-arg BASE_IMAGE_TAG=3.9.1.3 .

• Less Hard Coded Information within property files
  • make this more user friendly, i.e. so people can specify within docker file instead of property files

• Java 8
  • commons-math 3.6.1
  • dsiutils 2.4.2
  • fastutil-8.1.0
  • jsap 2.1
  • json
  • mason
  • mysql-connector 5.1.46
  • PaySim
  • slf4j
  • sux4j
  • WebGraph 3.6.1
• Python 2.7
  • networkx 1.10 (2.* will not work)
  • matplotlib
  • powerlaw

See Wiki page Directory Structure for details.

See Wiki page Quick Introduction to AMLSim for details.

sh scripts/build_AMLSim.sh
sh scripts/run_AMLSim.sh [SimulationName] [Steps]

• SimulationName: Simulation name
• Steps: Number of steps per simulation

Example:

sh scripts/run_AMLSim.sh sample 150

Before running the Python script, please check and edit configuration file prop.ini.

[InputFile]
directory = paramFiles/1K
alertPattern = alertPatterns.csv

Then, please run transaction graph generator and simulator scripts.

cd /path/to/AMLSim
python scripts/transaction_graph_generator.py prop.ini paramFiles/1K/accounts.csv paramFiles/1K/degree.csv paramFiles/1K/transactionType.csv
sh scripts/run_AMLSim.sh sample 150

python scripts/visualize/plot_transaction_graph.py [TransactionLog] [AlertID]

• TransactionLog: Log CSV file path from AMLSim (e.g. outputs/sample/sample_log.csv)
• AlertID: An alert ID to be visualized

python scripts/convert_logs.py [ConfFile] [TransactionLog]

• ConfFile: Configuration ini file for the data conversion (convert.ini)
• TransactionLog: Transaction log CSV file under outputs/(name)/ (e.g. outputs/sample/sample_log.csv)

Example:

python scripts/convert_logs.py convert.ini outputs/sample/sample_log.csv

sh scripts/clean_logs.sh