Big Data are growing at an exponential rate and it becomes necessary the use of tools and technologies to manage, process and visualize them in order to extract value. In this paper a micro-service based platform is presented for the composition, deployment and execution of Big Data Analytics (BDA) application workflows in several domains and scenarios is presented. ALIDA is a result coming from previous research activities by ENGINEERING. It aims to achieve a unified platform that allows both BDA application developers and data analysts to interact with it. Developers will be able to register new BDA applications through the exposed API and/or through the web user interface. Data analysts will be able to use the BDA applications provided to create batch/stream workflows through a dashboard user interface to manipulate and subsequently visualize results from one or more sources. The platform also supports the auto-tuning of Big Data frameworks deployment properties to improve metrics for analytics application. ALIDA has been properly extended and integrated into a software solution for the analysis of large amounts of data from the avionic industries. A use case within this context is then presented.
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.