< Back to previous page

Project

Mixed-initiative recommender systems: towards a next generation of recommender systems through user involvement.

Recommender systems that suggest relevant items to users have been researched extensively over the past decades. Whereas several algorithms have been deployed in numerous applications, important challenges need to be addressed before such systems can realise their full potential. Among others, the black box nature of recommender systems prevents users from providing input and feedback. As the predication of the current interest of the user is a challenging task, there is a need to develop mixed approaches that enable users to steer this process. In this project, we will research how we can support user control with interactive visualisation techniques. The objective is to enable the development of recommender systems that can be adapted on-the-fly to address different user needs.
Date:1 Oct 2016 →  30 Sep 2020
Keywords:recommender systems
Disciplines:Applied mathematics in specific fields