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.We computed the delta between the real and synthetic data using the sum of squared errors approach. This shows that MoMTSim can produce synthetic data that resemble real mobile money transaction data, thereby confirming the efficacy of the calibration algorithm for use in simulating complex financial ecosystems.
This data article introduces a labeled synthetic mobile money transaction dataset created using MoMTSim, a multi-agent-based simulation platform designed and validated specifically for mobile money transactions. MoMTSim toolkit simulates mobile money interactions, ensuring that the generated synthetic dataset closely mimics the statistical properties of real transaction data. This dataset encapsulates a wide range of transaction features, such as timestamps (step), transaction amounts, the initial and new account balances of both the initiator and recipient, participant IDs, and the types of transactions conducted. The included transaction types span deposits, withdrawals, transfers, payments, and debits. Each record in the dataset also carries a label that identifies whether the transaction is legitimate or fraudulent. The synthesis of this dataset using MoMTSim is described in this article and its structure and summary statistics are also presented. The dataset is particularly suitable for training and testing machine learning algorithms to detect financial fraud. Additionally, it holds the potential for benchmarking fraud detection algorithms and systems and validating synthetic data generation methodologies.
Mobile data collection systems (MDCS) in the health sector are of great benefit to health care providers and community workers especially in low-resource settings. MDCS enable the extension and provision of health services closer to the community by enabling data collection and diagnosis without the patient being in a hospital setting. MDCS, however, face a number security challenges including authentication and authorization of users, secure communication between a mobile client and the server, and secure application deployment. This paper provides a criteria and guidelines for evaluating an authentication model for MDCS. The criteria encompass key authentication dimensions including proper local and remote authentication, password management and recovery especially with no Internet connectivity. We assess the authentication models using two reference systems that are widely used in low-resource settings, namely, District Health Information Software (DHIS 2) and mUzima. The findings reveal gaps in the authentication model of the reference systems including insecure authentication, insecure storage of user credentials on the mobile device and no proper automatic logouts, among others.
Mobile Health Data Collection Systems (MHDCS) use electronic forms for data collection in place of paper surveys. Data is entered into the electronic forms by community health workers with smartphones. These systems are used in clinical trials and continuous monitoring of participants. Data collected in MHDCS is diverse with varying sensitivity levels. This therefore calls for the application of different security mechanisms to protect the data. In this paper, a data sensitivity classification model is proposed. It determines the sensitivity levels of form attributes depending on the context and sensitive parameters. The electronic form is the starting point of the data collection process. We augment the form with sensitivity levels and a mapping of security mechanisms to the sensitivity levels is made. Through threat modeling, we identify potential threats and possible mitigations. We demonstrate the feasibility of our approach by prototyping the proposed model into the Open Data Kit tool suite. Tests show that the security mitigations specified during form design are executed once the secure form is loaded on the mobile device during data collection. Our ultimate aim is to facilitate the addition of security requirements into the data collection processes right from the start of the design process.