Workshop summary

Nowadays, recommender systems are employed across a diverse set of application domains, not only supporting us in our decision making and choices but also helping us to discover and find new items, products, and services much more efficiently. The commonly used approach in recommender systems is receiver-centric (or user-centric) where the focus is on satisfying the receiver of the recommendations without any considerations for other business & strategic objectives or the objectives of the item and content providers . 

A recommender system that does not include strategic or business-related objectives is often referred to as an "organic" recommender system, emphasizing personalized recommendations with exclusive consideration for user relevance. Conversely, strategic, sponsored or utility-aware recommendations adopt a different perspective, with the objective optimizing for both user relevancy and some other kind of utility associated with those recommendations. In contrast to an organic recommender system, the focus of a strategic recommender system is to identify the most “relevant” users for a given item to maximize utility. 

Utility can be defined in many ways depending on the problem we are solving and the domain on which the recommender systems in operating. For example, on many two-sided matching platforms, a recommendation would have higher utility if both sides are interested in each other (host and guest on Airbnb, seller and buyer on Meta marketplace, candidate and job listing on Linkedin). It could also be monetary where one recommendation might have a higher profit margin than another when they might have similar relevance from the user's perspective. Other types of utility could be also considered such as fairness and transparency, 

In real-world applications of recommender systems, aligning user-centric recommendation with overarching strategies supporting content creators in their growth has become imperative in many multi-sided platforms. With advanced development of technology and research in the domain, the pressing need for a closer integration of recommender systems with both long and short term strategic goals becomes more clear. This introduces various challenges that are worth further investigation by the research community and industry practitioners.

Workshop topics

We encourage submissions that address the challenges related to having multiple objectives or multiple stakeholders in recommender systems.  The topics of interest for the workshop include, but are not limited to:

• Recommendation with multiple stakeholders

• Utility-aware recommender systems

• Applications of personalization in advertising and promotions   

• Recommender systems with multiple objectives

• Estimation and optimization methods for the long-term value of recommender systems

• Long-term community or audience growth for recommended items

• Explainable recommendations, especially for strategic and utility-aware recommendations.

• Methods for estimating trade-offs between user retention and satisfaction and a utility value of recommendations

• The impact of different objectives on the short-term and long-term success of the recommender systems.

• Simulation for experimentation in multi-objective, multi-stakeholder recommenders, and long-term user satisfaction. 

• Users’ trust in recommendations for non-organic recommendations.

Workshop Chairs:

• Himan Abdollahpouri (Spotify, USA)

• Tonia Danylenko (Spotify, Sweden)

• Masoud Mansoury (TU Delft, Netherlands)

• Babak Loni (Meta, Netherlands)

• Daniel Russo (Columbia Business School, USA)

• Mihajlo Grbovic (Airbnb, USA)