Patterns of Multistakeholder Recommendation

TL;DR

This paper explores multistakeholder recommender systems, identifying various utility patterns and providing a taxonomy of system types, highlighting both existing and potential implementations in personalized recommendation contexts.

Contribution

It introduces a taxonomy of multistakeholder recommendation systems based on stakeholder utility patterns, advancing understanding of diverse application designs.

Findings

Identified key patterns of stakeholder utility in multistakeholder recommendations

Provided a comprehensive taxonomy of possible system architectures

Highlighted gaps between existing systems and potential designs

Abstract

Recommender systems are personalized information systems. However, in many settings, the end-user of the recommendations is not the only party whose needs must be represented in recommendation generation. Incorporating this insight gives rise to the notion of multistakeholder recommendation, in which the interests of multiple parties are represented in recommendation algorithms and evaluation. In this paper, we identify patterns of stakeholder utility that characterize different multistakeholder recommendation applications, and provide a taxonomy of the different possible systems, only some of which have currently been implemented.