Home // eKNOW 2016, The Eighth International Conference on Information, Process, and Knowledge Management // View article

Recommendation Techniques on a Knowledge Graph for Email Remarketing

Authors:
László Grad-Gyenge
Peter Filzmoser

Keywords: knowledge graph; recommender system; spreading activation; network science; email remarketing

Abstract:
The knowledge graph, which is an ontology based representation technique, is described to model the information necessary to conduct collaborative filtering, content-based filtering and knowledge based recommendation methods. Spreading activation and network science based recommendation methods are presented and evaluated. The evaluation measures are calculated on top list recommendations, where rating estimation is not necessary. In the experiment, click-through rates are measured and presented based on the email based remarketing activity of an electronic commerce system. Our primary result shows the improved recommendation quality of spreading activation based methods compared to the human expert.

Pages: 51 to 56

Copyright: Copyright (c) IARIA, 2016

Publication date: April 24, 2016

Published in: conference

ISSN: 2308-4375

ISBN: 978-1-61208-472-5

Location: Venice, Italy

Dates: from April 24, 2016 to April 28, 2016