FraudTwin documentation#
FraudTwin is a deterministic payment-world simulator for fraud detection, graph analysis, data engineering, and machine-learning experiments.
The same configuration and seed produce the same entities, events, labels, and output fingerprints, so difficult fraud cases become explainable, testable, and reproducible.
Install and run#
$ poetry install
$ poetry run fraudtwin config validate configs/minimal.yaml
$ poetry run fraudtwin generate configs/minimal.yaml --output-dir ./runs
Start here#
Install FraudTwin, create a small run, and learn what the generated manifest and Parquet files mean.
Learn FraudTwin through short, executable paths grouped by workflow.
Configure runs, build datasets, operate integrations, and solve focused implementation tasks.
Understand determinism, lifecycles, point-in-time data, fraud graphs, and data quality.
Look up the Python API, configuration, CLI, and data contracts.
Need a guided route?#
Use Choose your path if you want a recommended starting point based on your goal or experience. It is an onboarding aid, not a second documentation hierarchy.
How a run becomes an experiment#
configuration → entities → behavior → payments → fraud/workflow → datasets / graphs / benchmarks
Each layer keeps stable identities and causal timestamps. Operational views contain only information available at the selected time; oracle artifacts keep the complete explanation for evaluation and audit.