Home // International Journal On Advances in Intelligent Systems, volume 9, numbers 3 and 4, 2016 // View article

Knowledge Graph based Recommendation Techniques for Email Remarketing

Authors:
László Grad-Gyenge
Hannes Werthner
Peter Filzmoser

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

Abstract:
This paper presents the knowledge graph, a graph based information modelling technique. The method generalizes the concept of information sources and defines a hybridization technique at the information representation level. Depending on the amount of collaborative and content-based information available, the balance of the hybridization is also discussed. The principles of the defined calculation methods, as generalization and transitivity facilitate the paradigm of relatedness. To evaluate the efficiency of the knowledge graph, graph based recommendation calculation techniques are defined and evaluated in an email remarketing activity, a real-world recommendation scenario. The results show that the spreading activation based recommendation technique is capable to increase the performance of the remarketing task.

Pages: 514 to 531

Copyright: Copyright (c) to authors, 2016. Used with permission.

Publication date: December 31, 2016

Published in: journal

ISSN: 1942-2679