Large-scale automated forecasting for network safety and security monitoring

Abstract

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.