In the construction of a telecom-fraud risk warning and intervention-effect prediction model, how to apply multivariate heterogeneous data to the front-end prevention and management of telecommunication network fraud has become one of the focuses of this research. The Bayesian network-based fraud risk warning and intervention model was designed by taking into account existing data accumulation, the related literature, and expert knowledge. The initial structure of the model was improved by utilizing City S as an application example, and a telecom-fraud analysis and warning framework was proposed by incorporating telecom-fraud mapping. After the evaluation in this paper, the model shows that age has a maximum sensitivity of 13.5% to telecom-fraud losses; anti-fraud propaganda can reduce the probability of losses above 300,000 yuan by 2%; and the overall telecom-fraud losses show that more occur in the summer and less occur in the autumn, and that the Double 11 period and other special time points are prominent. The model in this paper has good application value in the real-world field, and the analysis of the early warning framework can provide decision support for the police and the community to identify the groups, locations, and spatial and temporal environments prone to fraud, to combat propaganda and provide a timely warning to stop losses.
A dynamic distributed decisionmaking (DDD) environment for Naval command and control is being utilized for experimentation on the cooperation of human decisionmakers (DMs) as they attempt to attain common goals. To support this experimentation, ADAM/DDD has been developed, so that scenarios which contain DMs, their interactions, platforms (ships, planes, etc.), subplatforms (a ship contains planes, etc.), and tasks (contacts to be processed by the team), may be specified. Inherent in this complex database are inter-dependencies or pmpugations that characterize automatic changes that must occur whenever portions of the scenario are modified, in order to ensure data consistency. This paper reports on ADAM/DDD, focusing on its support for propagation. I IntroductionIn a dynamic distributed decisionmaking (DDD) environment, human decisionmakers (DMs) must collect and interpret, potentially large quantities of diverse, disparate information. Through the DDD environment, a team of possibly geographically separated DMs, coordinate to share information, resources, and activities, in order to attain common goals through the decision process, in a dynamic and uncertain environment. Consequently, the goal of our ongoing, multi-disciplinary project on DDD for Naval command, control, and communication [lo], has been to evaluate and understand exactly how a team of DMs interact with one another to arrive at decisions.To conduct different experiments using the DDD environment, a database of information and facts, referred to as a scenario, must be provided. For example, one scenario could have four DMs organized into a hierarchical group, with communication restricted between the leader and the subordinates. Other parameters for the scenario would be system oriented (i.e., the time for the simulation, communication delays, etc.), the platforms that are defined (i.e., the ships, planes, etc.), the subplatforms (i.e., a ship contains planes, etc.), and the tasks (i.e., contacts to be processed by the team). As different experiments are conducted, new scenarios must be developed.hierarchy to a leaderless group of equals, so that the effect of the team organization can be evaluated. While similar to the first example, in this case we may need to modify other portions of the new scenario (i.e., platforms, subplatforms, tasks, etc.) that are dependent on the team structure. Thus, the scenario designer must know and understand all of the required database information and facts, as well as their complex inter-relationships, in order to insure that a consistent scenario for a desired experiment is specified. If these modifications are managed manually, it is quite often a t the expense of data consistency and designer-introduced errors.To overcome these potential consistency problems, thereby facilitating DDD experimentation, we have developed ADAM/DDD, a design tool that promotes the specification of a complete and accurate scenario for a given experiment. ADAM/DDD is a multi-phase, window-based, and graphically-oriented scenario desig...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.