Pinar Karagoz: Utility Based Mining of Sequential Patterns

Tapahtuman tyyppi: 
23.08.2017 - 14:15 - 15:30
Pinar Karagoz
Exactum B222

Guest lecture
Pinar Karagoz: Utility Based Mining of Sequential Patterns

Abstract:  High utility sequential pattern mining has been considered as an important research problem and a number of relevant algorithms have been proposed for this topic. The main challenge of high utility sequential pattern mining is that, the search space is large and the efficiency of the solutions is directly affected by the degree at which they can eliminate the candidate patterns. Therefore, the efficiency of any high utility sequential pattern mining solution depends on its ability to reduce this big search space. In this talk, I will present the problem and the techniques to improve pruning of candidate patterns, and then describe a more general framework to define utility in terms of user-defined pattern scoring, applied on web usage data.

Short Bio:  Pinar Karagoz is an Associative Professor in Computer Engineering Department of Middle East Technical University. She received her PhD. degree from the same department  in 2003 and worked as a visiting researcher in State University of New York (SUNY) at Stony Brook. Her research interests include data mining, web usage mining, social network analysis, information extraction from web, semantic web services, web service discovery and composition. Recently she served in the management commitee of the COST Action ENERGIC (European Network Exploring Research into Geospatial Information Crowdsourcing).
18.08.2017 - 15:48 Hannu Toivonen
18.08.2017 - 15:48 Hannu Toivonen