PixSim: a calibrated open-source simulator of instant-payment fraud, recovery and interdiction under analyst capacity constraints

Battle Count: 0

Low direct relevance to quantitative trading strategies. The paper focuses on fraud interdiction and operational risk in payment rails, not asset pricing or trading execution. However, the queueing and stochastic control methods could theoretically apply to order execution under capacity constraints.

High complexity. Requires implementing a discrete-event simulator with multiple interacting modules (population, traffic, fraud rings, scorer, policy, analyst queue, MED clock). Calibration involves bisection searches against specific regulatory observables.

High reproducibility. The simulator is open-source (Apache-2.0), code and data are archived on Zenodo, environment is pinned (Python 3.13, specific library versions), and all parameters are sourced or registered as assumptions. Full-scale runs are verified against BCB statistics.