Mon Jun 20, 2011 at 11:00
A108 Via Sommarive, 5
Recommendation systems provide advice on movies, products, travel, leisure activities, and many other topics,and have become very popular in systems, such as Netflix and Amazon. Many recommendation approaches have been proposed both by the industry and academia but most of them are 'hard-wired' into the system making experimentation with and implementation of new recommendation paradigms cumbersome.
In this talk, I will present FlexRecs, a framework that decouples the definition of a recommendation process from its execution and supports flexible recommendations over structured data. In FlexRecs, a recommendation approach can be defined declaratively as a high-level parameterized workflow comprising traditional relational operators and new operators that generate or combine recommendations. I will describe a prototype flexible recommendation engine that realizes the proposed framework and can capture multiple, existing or novel, recommendations easily and with reasonable performance.
About the speaker
Georgia Koutrika is currently with the Information Integration Group at IBM Almaden at San Jose, USA.
Prior to that, she was a postdoctoral researcher at the CS Department of Stanford University and a visiting collaborator at HP Labs at Palo Alto, USA. She obtained her diploma and her PhD in Computer Science from the University of Athens' Department of Informatics and Telecommunications in Greece.
Her research interests include web information integration, entity resolution, personalized search and recommendations, social networks, user preference models, keyword search and user profiling.
She is in the steering committee of PersDB (Int'l Workshop on Personalized Access, Profile Management, and Context Awareness in Databases) and she has served as a PC co-chair of four workshops and as a PC member in several conferences, including SIGMOD, ICDE, WWW and EDBT. She has served as a reviewer for various journals (including ACM TODS, TKDE, IS).
Contact: Ioannis Velegrakis