Netflix recommendations for groups

Abstract

In this era of overabundant information and content, people increasingly rely on recommender systems to identify those information items that best meet their needs and interests. Movie recommender systems, like the one used by Netflix, attempt to predict which films a given person will enjoy watching. While these systems help single individuals making decisions, they provide limited support for groups of people. This work explores how to create recommender systems for groups that can combine multiple user profiles and predict which movies a group of users will collectively enjoy the most. We built a prototype using Netflix REST API based on the results of a formative study of the watching habits of 60 actual Netflix users and examined their views of how a group recommendation system would fit in with their current habits. We conducted a preliminary evaluation with a focus group which validated our approach to group recommendations, revealing that this type of system could facilitate social interactions by sparking discussion about movies, directors, and actors among viewers. This prototype provides a valuable platform for further exploring group decision making in this context.

An Exploration of Account Sharing Practices on Media Platforms

“…al. [2] explores the possibility of recommender systems for groups of users by combining multiple user profles. This would result in recommendations that the group, as a collective would be able to relate to, as opposed to the owner of single user profle.…”

“…[25] puts it however, "we lack a systematic understanding of the nature of device and account sharing, across multiple device and account types, [both] in households", across locations and beyond the assumed generic user cohort. Research has begun exploring various aspects of this domain [9,14,20,25,30,35], particularly within media experiences [2,11,15]. Industry has also become sensitive to these needs, as refected in the recent additions of profles within accounts on Netfix and Disney+.…”

Follow your neighbours and engage in a new culture

“…Recommender systems help users to make clear decisions and suggest other options. For example, in Netflix, the actor, director, or genre of the previously watched movies is used to create a list of suggested new choices based on the users likes, interests and history [2].…”

Fuzzy Group Decision Making for influence-aware recommendations

“…Family Interactive TV [16] also filters television programs according to the viewers' preferences and uses implicit relevance feedback assessed through the actual program the viewer has chosen for watching. In [17] a prototype GRS for the popular Netflix media streaming service is also proposed. [18] assists a group of people to agree on the desired attributes of a planned joint holiday.…”