Large-scale automated forecasting for network safety and security monitoring

R. Naveiro, S. Rodríguez-Santana, D. Ríos Insua

Applied Stochastic Models in Business and Industry Vol. 35, nº. 3, pp. 431 - 447

Summary:

Large-scale real-time streaming data pose major challenges to forecasting, in particular, defying the presence of human experts to perform the required analysis. We present here a class of models and methods used to develop an automated, scalable, and versatile system for large-scale forecasting oriented toward network safety and security monitoring. Our system provides short- and long-term forecasts and uses them to detect issues, well in advance, that might take place in relation with multiple Internet-connected devices.

Keywords: Bayesian methods, dynamic models, forecasting, network monitoring, real-time predictive analytics

JCR Impact Factor and WoS quartile: 1,175 - Q2 (2019); 1,300 - Q2 (2023)

DOI reference: https://doi.org/10.1002/asmb.2436

Published on paper: May 2019.

Published on-line: February 2019.

Citation:
R. Naveiro, S. Rodríguez-Santana, D. Ríos Insua, Large-scale automated forecasting for network safety and security monitoring. Applied Stochastic Models in Business and Industry. Vol. 35, nº. 3, pp. 431 - 447, May 2019. [Online: February 2019]