Despite the need for data in a time of general digitization of organizations, many challenges are still hampering its shared use. Technical, organizational, legal, and commercial issues remain to leverage data satisfactorily, specially when the data is distributed among different locations and confidentiality must be preserved. Data platforms can offer “ad hoc” solutions to tackle specific matters within a data space. MUSKETEER develops an Industrial Data Platform (IDP) including algorithms for federated and privacy-preserving machine learning techniques on a distributed setup, detection and mitigation of adversarial attacks, and a rewarding model capable of monetizing datasets according to the real data value. The platform can offer an adequate response for organizations in demand of high security standards such as industrial companies with sensitive data or hospitals with personal data. From the architectural point of view, trust is enforced in such a way that data has never to leave out its provider’s premises, thanks to federated learning. This approach can help to better comply with the European regulation as confirmed from a legal perspective. Besides, MUSKETEER explores several rewarding models based on the availability of objective and quantitative data value estimations, which further increases the trust of the participants in the data space as a whole.
Abstract-Agent-based systems have become a very attractive approach for dealing with the complexity of modern software applications and have proved to be useful and successful in some industrial domains. However, engineering such systems is still a challenge due to the lack of effective tools and actual implementations of very interesting and fascinating theories and models. In this area the so-called intentional stance of systems can be very helpful to efficiently predict, explain, and define the behaviour of complex systems, without having to understand how they actually work, but explaining them in terms of some mental qualities or attitudes, rather than in terms of their physical or design stance.In this paper we present the PRACTIONIST framework, that supports the development of PRACTIcal reasONIng sySTems according to the BDI model of agency, which uses some mental attitudes such as beliefs, desires, and intentions to describe and specify the behaviour of system components. We adopt a goal-oriented approach and a clear separation between the deliberation and the means-ends reasoning, and consequently between the states of affairs to pursue and the way to do it. Moreover, PRACTIONIST allows developers to implement agents able to reason about their beliefs and the other agents' beliefs, expressed by modal logic formulas.
Frauds in financial services are an ever-increasing phenomenon, and cybercrime generates multimillion revenues, therefore even a small improvement in fraud detection rates would generate significant savings. This chapter arises from the need to overcome the limitations of the rule-based systems to block potentially fraudulent transactions. After mentioning the limitations of rule-based approach, this chapter explains how machine learning is able to address many of these limitations and, more effectively, identify risky transactions. A novel AI-based fraud detection system – built over a Data Science and Machine Learning – is presented for the pre-processing of transaction data and model training in a batch layer (to periodically retrain the predictive model with new data) while in a stream layer, the real-time fraud detection is handled based on new input transaction data. The architecture presented makes this solution a valuable tool for supporting fraud analysts and for automating the fraud detection processes.
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.