fintech-kMC: Agent based simulations of financial platforms for design and testing of machine learning systems
This provides a reproducible method for testing AI/ML models in fintech applications, but it is incremental as it applies an existing simulation approach to a specific domain.
The authors tackled the problem of generating synthetic data for machine learning in financial platforms by developing fintech-kMC, an agent-based simulation tool that produces interpretable and realistic data for model validation and testing.
We discuss our simulation tool, fintech-kMC, which is designed to generate synthetic data for machine learning model development and testing. fintech-kMC is an agent-based model driven by a kinetic Monte Carlo (a.k.a. continuous time Monte Carlo) engine which simulates the behaviour of customers using an online digital financial platform. The tool provides an interpretable, reproducible, and realistic way of generating synthetic data which can be used to validate and test AI/ML models and pipelines to be used in real-world customer-facing financial applications.