Recommender Systems in Industry: A Netflix Case Study

Amatriain, Xavier; Basilico, Justin

doi:10.1007/978-1-4899-7637-6_11

Cited by 80 publications

(65 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…RSs are widely used in what we referred to as Bcontent intensive applications^, characterized by a very large amount of online multimedia information, either made available by the service provider or user generated (think of the 3 billion videos uploaded on YouTube by late 2012 [57] or the 20 million songs on Spotify [66]). In these contexts, the dimension of the multimedia search space and the availability of an enormous set of choices may slow down the user's exploration, reduce the visibility of some potentially interesting items, and increase the complexity of the decision making process [8,28,29,59,71,79]. Complementing (and in some cases even replacing) free navigation and traditional query-based paradigms, recommendations can alleviate the above problems, and reduce the information overload by focusing the search space and orienting the user's decisions [9].…”

Section: Introductionmentioning

confidence: 99%

User interface patterns in recommendation-empowered content intensive multimedia applications

Cremonesi

Elahi

Garzotto

2016

Multimed Tools Appl

View full text Add to dashboard Cite

Design Patterns (DPs) are acknowledged as powerful conceptual tools to improve design quality and to reduce time and cost of the development process by effect of the reuse of Bgood^design solutions. In many fields (e.g., software engineering, web engineering, interface design) patterns are widely used by practitioners and are also investigated from a research perspective. Still, they have been seldom explored in the arena of Recommender Systems (RSs). RSs provide suggestions (Brecommendations^) for items that are likely to be appropriate for the user profile, and are increasingly adopted in content-intensive multimedia applications to complement traditional forms of search in large information spaces. This paper explores RSs through the lens of User Interface (UI) Design Patterns. We have performed a systematic analysis of 54 recommendation-empowered content-intensive multimedia applications, in order to: (i) discover the occurrences of existing domain independent UI patterns; (ii) identify frequently adopted UI solutions that are not modelled by existing patterns, and define a set of new UI patterns, some of which are specific of the interfaces for recommendation features while others can be useful also in a broader context. The results of our inspection have been discussed with and evaluated by a team of experts, leading to a consolidated set of 14 new patterns that are reported in the paper. Reusing pattern-based design solutions instead of building new solutions from scratch enables novice and expert designers to build good UIs for Recommendation-empowered content intensive multimedia applications more effectively, and ultimately can improve the UX experience in this class of systems. From a broader perspective, Multimed Tools Appl

show abstract

Section: Introductionmentioning

confidence: 99%

User interface patterns in recommendation-empowered content intensive multimedia applications

Cremonesi

Elahi

Garzotto

2016

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Meanwhile, accuracy, traditional serendipity and diversity remain almost the same, as observation According to observation 5, our algorithm underperforms the non-personalized baseline in terms of NDCG@n. Accuracy of POP is generally relatively high, as users on average tend to give high ratings to popular movies (Amatriain and Basilico, 2015). However, accuracy in this case is unlikely to reflect user satisfaction, as users are often already familiar with popular movies suggested.…”

Section: Sog Slightly Outperforms Sogbasic In Terms Ofmentioning

confidence: 99%

A Serendipity-Oriented Greedy Algorithm for Recommendations

Kotkov

Veijalainen

Wang

2017

Proceedings of the 13th International Conference on Web Information Systems and Technologies

View full text Add to dashboard Cite

Abstract:Most recommender systems suggest items to a user that are popular among all users and similar to items the user usually consumes. As a result, a user receives recommendations that she/he is already familiar with or would find anyway, leading to low satisfaction. To overcome this problem, a recommender system should suggest novel, relevant and unexpected, i.e. serendipitous items. In this paper, we propose a serendipity-oriented algorithm, which improves serendipity through feature diversification and helps overcome the overspecialization problem. To evaluate our algorithm and compare it with others, we employ a serendipity metric that captures each component of serendipity, unlike the most common metric.

show abstract

“…These networks serve up to hundreds of millions of users (for instance Facebook reported 1.15 billion monthly active users in June 2013 [8]), and must select recommendation techniques able to scale to their user base, while being amenable to the highly distributed infrastructures in which these services are typically deployed. The ability to scale and distribute recommendation algorithms has been shown in the past to play a key role in their acceptability: Netflix for instance revealed in 2012 that it had not adopted the winning algorithms of its own one million dollar Netflix prize, in part because of the engineering challenges raised to port the algorithm to their distributed infrastructure (hosted by Amazon) [1].…”

Section: Problem Statementmentioning

confidence: 99%

“…Implementing a recommendation mechanism that works for such a large user base over terabytes of data is a highly challenging task: an ideal solution should be accurate, lightweight, and easily scale to the distributed and cloud environments in which modern recommenders are being deployed [1]. Traditional approaches to user recommendation in social networks have so far heavily relied on topological metrics to identify new users or items that might be of interest to a user.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cheap and Cheerful: Trading Speed and Quality for Scalable Social-Recommenders

Kermarrec¹,

Taı̈ani²,

Tirado³

2015

Distributed Applications and Interoperable Systems

View full text Add to dashboard Cite

Abstract. Recommending appropriate content and users is a critical feature of on-line social networks. Computing accurate recommendations on very large datasets can however be particularly costly in terms of resources, even on modern parallel and distributed infrastructures. As a result, modern recommenders must generally trade-off quality and computational cost to reach a practical solution. This trade-off has however so far been largely left unexplored by the research community, making it difficult for practitioners to reach informed design decisions. In this paper, we investigate to which extent the additional computing costs of advanced recommendation techniques based on supervised classifiers can be balanced by the gains they bring in terms of quality. In particular, we compare these recommenders against their unsupervised counterparts, which offer lightweight and highly scalable alternatives. We propose a thorough evaluation comparing 11 classifiers against 7 lightweight recommenders on a real Twitter dataset. Additionally, we explore data grouping as a method to reduce computational costs in a distributed setting while improving recommendation quality. We demonstrate how classifiers trained using data grouping can reduce their computing time by 6 while improving recommendations up to 22% when compared with lightweight solutions.

show abstract

Recommender Systems in Industry: A Netflix Case Study

Cited by 80 publications

References 67 publications

User interface patterns in recommendation-empowered content intensive multimedia applications

User interface patterns in recommendation-empowered content intensive multimedia applications

A Serendipity-Oriented Greedy Algorithm for Recommendations

Cheap and Cheerful: Trading Speed and Quality for Scalable Social-Recommenders

Contact Info

Product

Resources

About