Real-world challenges for mining streaming data: lessons learned in chemical industry

Abstract
Nowadays large amounts of streaming industrial, transactional or sensing data present new opportunities for real time analytics and personalized services. Predictive models, built on such data, need to be robust to ever changing environment and be able to autonomously diagnose and update themselves taking into account the most recent data, otherwise their accuracy will soon deteriorate. In the last decade mining evolving data streams has become a 'hot' research topic, many adaptive learning algorithms have been developed; however,  such algorithms are still rarely employed in practice. In this talk we will discuss six real-world challenges for learning from evolving data streams illustrated by a practical case from the chemical production industry and point out some open research directions for data streams.

Bio
Indrė Žliobaitė is a postdoctoral researcher with the Finnish Centre of Excellence for Algorithmic Data Analysis Research (Algodan). Prior to that she was a research task leader in the INFER.eu project, a data analytics secondee at Evonik Industries and a lecturer at Bournemouth University. She obtained her PhD from Vilnius University in 2010. She has six years of experience in credit risk analysis at commercial banks. For further information see http://zliobaite.googlepages.com