Modeling intents of web site visitors

Abstract: Predictive Web analytics is aimed at understanding behavioral patterns of users of various web-based applications or services in e-commerce, mass-media, and entertainment industries. Accurately modeling user intents and predicting the probability of desired actions on the web (product purchases, membership registrations, newsletter subscriptions, software downloads, accessing certain information resources, clicking ad banners) in specific circumstances would enable us to achieve better personalization and adaptation to diverse customer needs and preferences.
In different personalization tasks formulated as some optimization problem, user intent or user context in general changes over time. In this talk I will give an overview of a few application scenarios and computational approaches that we currently consider to model changing user intents.

Short bio: Mykola Pechenizkiy is Assistant Professor at the Department of Computer Science, Eindhoven University of Technology, the Netherlands. He received his PhD from the Computer Science and Information Systems department at the University of Jyvaskyla, Finland in 2005. He has broad expertise and research interests in data mining and data-driven intelligence, and its application to various (adaptive) information systems serving industry, commerce, medicine and education. He has co‐authored over 70 publications and co-organized several workshops (HaCDAIS@ECMLPKDD2010 & IEEE ICDM 2011, LEMEDS@AIME2011, DAH@HT2011), conferences (IEEE CBMS 2008, BNAIC 2009, EDM 2011) and tutorials (at IEEE CBMS 2010, ECML/PKDD 2010, PAKDD 2011) in these areas. Recently, he has co-edited the Handbook of Educational Data Mining and served as a guest editor of the special issues with SIGKDD Explorations (ACM), Evolving Systems (Springer), Data and Knowledge Engineering (Elsevier) and Artificial Intelligence in Medicine (Elsevier) journals. Currently and/or in the recent past he has taken a leading role in NWO HaCDAIS, STW CAPA, EIT ICT Labs Stress@Work and NL Agency CoDAK projects information on which can be found at http://www.win.tue.nl/~mpechen/