HKBU  |  SCI  |  BUniPort  |  Library  |  Alumni  |  Job Vacancies  |  Intranet  |  Sitemap        
Undergraduate Admissions
Taught Postgraduate Admissions
Research Postgraduate Admissions
Job Vacancies
News & Achievements
Research Highlights
Contact & Direction

Department of Computer Science Colloquium
2010 Series

Lifestyle Search and Recommendation*

Prof. Wayne Wobcke
School of Computer Science and Engineering
University of New South Wales

Date: December 10, 2010 (Friday)
Time: 2:30 - 3:30 pm
Venue: SCT909, Cha Chi Ming Science Tower, Ho Sin Hang Campus

Most web-based product search interfaces enable search using technical criteria. However these interfaces are difficult to use for users without domain knowledge, especially when products are highly technical and/or where the market contains many items that are very similar and thus hard to differentiate (e.g. cameras, computers). The aim of "lifestyle search" is to provide a search mechanism for naive users that operates over a space more reflective of the user's interests (their "lifestyle"), rather than the space of technical product specifications.

This talk describes the Lifestyle Car Finder, an application of lifestyle search in the domain of new cars. A new car database with around 2000 makes, models and model variants is used as the basis of ten lifestyle functions, including four primary car types (family car, sports car, city car and off-roader) and six secondary attributes (performance, safety features, luxury features, fuel efficiency, eco-friendliness, towing capacity and car size), which are defined using both expert knowledge and machine learning. The Lifestyle Car Finder incorporates various modes of navigation in the lifestyle space (refinement, critiquing and breadcrumbs) and decision support aids (simple explanations, similar cars and technical specifications).

A user study involving 9 users with a range of realistic scenarios will be described, focusing on the use of the different navigation strategies and decision support aids as determined from user logs, and a qualitative evaluation of user satisfaction. Broadly speaking, users were highly satisfied with the system and felt they were confident in their decisions made using the system.

*Joint work with Hesam Ziaei and Anna Wong, funded by Smart Services Cooperative Research Centre

Wayne Wobcke is an Associate Professor in the School of Computer Science and Engineering at the University of New South Wales, where he currently leads the Personalisation Project for Smart Services Cooperative Research Centre looking at applications of data mining in recommender systems. Previously he was Programme Manager within Smart Internet Technology Cooperative Research Centre where he led several research projects on dialogue management and personalisation in software agents. Prior to joining UNSW he spent three years at British Telecom Labs in the UK where he was part of a team that received the British Computer Society Medal for Innovation in Information Technology for work on the Intelligent Assistant.

********* ALL INTERESTED ARE WELCOME ***********
(For enquiry, please contact Computer Science Department at 3411 2385)
Copyright © 2021. All rights reserved.Privacy Policy
Department of Computer Science, Hong Kong Baptist University
Hong Kong Baptist University