The analysis of very large data sources requires scalable systems to reduce execution time and make the Big Data paradigm viable. Cloud infrastructures can be effectively used as scalable computing and storage platforms for implementing high-performance data analysis services. Nubytics is a Softwareas- a-Service (SaaS) system that exploits Cloud facilities to provide efficient services for analyzing large datasets. The system allows users to import their data to the Cloud, extract knowledge models using high performance data mining services, and exploit the inferred knowledge to predict new data and behaviours. In particular, Nubytics provides data classification and regression services that can be used in a variety of scientific and business applications. Scalability is ensured by a parallel computing approach that fully exploits the resources available on a Cloud. The paper describes the main services provided by Nubytics and presents an experimental performance analysis to show its scalability.
Nubytics: Scalable Cloud Services for Data Analysis and Prediction
Eugenio Cesario;
2016
Abstract
The analysis of very large data sources requires scalable systems to reduce execution time and make the Big Data paradigm viable. Cloud infrastructures can be effectively used as scalable computing and storage platforms for implementing high-performance data analysis services. Nubytics is a Softwareas- a-Service (SaaS) system that exploits Cloud facilities to provide efficient services for analyzing large datasets. The system allows users to import their data to the Cloud, extract knowledge models using high performance data mining services, and exploit the inferred knowledge to predict new data and behaviours. In particular, Nubytics provides data classification and regression services that can be used in a variety of scientific and business applications. Scalability is ensured by a parallel computing approach that fully exploits the resources available on a Cloud. The paper describes the main services provided by Nubytics and presents an experimental performance analysis to show its scalability.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


