MoMTSim: A Multi-Agent-Based Simulation Platform Calibrated for Mobile Money Transactions

• Published in: IEEE access 2024, Vol.12, p.120226-120238
• Main Authors: Azamuke, Denish, Katarahweire, Marriette, Bainomugisha, Engineer
• Format: Article
• Language: English
• Subjects: Agent-based models; Algorithms; Calibration; Data models; Datasets; Ecosystems; Fraud; Kolmogorov-Smirnov test; mobile money; model calibration; Multi-agent systems; Multi-agent-based simulation; Multiagent systems; Online banking; Parameter identification; Simulation; Simulation models; Social networking (online); Statistical methods; Synthetic data; Urban planning
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3439012

Research on multi-agent systems has extensively modeled real-world phenomena across various domains including epidemiology, urban planning, and financial transactions. These systems often struggle to produce agent behaviors that comprehensively capture the dynamics of the real-world ecosystem and the unique behaviors of each agent type. Furthermore, the limited explainability of these models due to non-iterative calibration poses significant challenges. This paper introduces an iterative model calibration algorithm that dynamically adjusts the multitude of parameters in a multi-agent simulation platform. Initially treating the simulation model as a black box, our method refines simulation parameters through cycles of adjustments based on clusters of observed behaviors comprising the behavior of both agents and actors. This approach allows for the identification and correction of inaccuracies, introduces new parameters, and discards erroneous ones within the agent-based model as demonstrated in a Mobile Money Transaction Simulator (MoMTSim). The calibration algorithm enhances the realism and applicability of the simulation model by ensuring that the generated synthetic datasets closely mirror real transaction data. The effectiveness of this calibration method was determined by validating the generated data through comparing the real and synthetic datasets using statistical methods including the Kolmogorov-Smirnov test, the sum of squared errors (SSE) method, and Bland-Altman plots. We computed the delta between the real and synthetic data using the SSE approach and found that the synthetic datasets resemble real data. This shows that MoMTSim effectively generates synthetic data that closely matches real mobile money transaction data, validating the accuracy of our model calibration algorithm in simulating complex financial ecosystems.