Daily-deal applications are popular implementations of online advertising strategies
that offer products and services to users based on their personal profiles. Current
implementations are effective but can frustrate users with irrelevant deals due to stale
profiles. To fully exploit the value creation and revenue generation potential of these
applications, deals must become smarter. This research presents SmarterDeals, a deal
recommendation system that exploits users changing personal context information to
deliver highly relevant offers. To improve the relevance of offers, SmarterDeals relies
on collaborative filtering recommendation algorithms and SmarterContext, our adaptive
context management framework. SmarterContext provides SmarterDeals with
up-to-date information about users locations as well as product and service preferences
gathered from their past and present web interactions and experiences. We
validated our approach using a data set of 271,418 product and service category ratings
and 65,411 real users. We present our results using a comparative analysis that
involves other well known recommendation approaches. / Graduate
| Identifer | oai:union.ndltd.org:uvic.ca/oai:dspace.library.uvic.ca:1828/4347 |
| Date | 12 December 2012 |
| Creators | Ebrahimi, Sahar |
| Contributors | Muller, Hausi A., Thomo, Alex |
| Source Sets | University of Victoria |
| Language | English, English |
| Detected Language | English |
| Type | Thesis |
| Rights | Available to the World Wide Web |
Page generated in 0.0367 seconds