Challenges in Search on Streaming Services: Netflix Case Study

  title={Challenges in Search on Streaming Services: Netflix Case Study},
  author={Sudarshan Lamkhede and Sudeep Das},
  journal={Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval},
  • Sudarshan Lamkhede, Sudeep Das
  • Published 11 March 2019
  • Computer Science
  • Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval
We discuss salient challenges of building a search experience for a streaming media service such as Netflix. We provide an overview of the role of recommendations within the search context to aid content discovery and support searches for unavailable (out-of-catalog) entities. We also stress the importance of keystroke-level Instant Search experience, and the technical challenges associated with implementing it across different devices and languages for a global audience. 

Figures and Tables from this paper

Recommendations and Results Organization in Netflix Search
This talk discusses the importance of producing search results that go beyond traditional keyword-matches to effectively satisfy users’ search needs in the Netflix entertainment setting and their approach to leverage recommendations in the context of Search and to effectively organize search results to provide a product experience that meaningfully adds value for users.
Deep Learning for Recommender Systems: A Netflix Case Study
The challenges encountered and lessons learned in using deep learning for recommender systems at Netflix are outlined and some of the take-aways that may generalize to other applications beyond Netflix are summarized.
Labor, classification and productions of culture on Netflix
Examination of promotional practices Netflix employs via Twitter and its automated recommendation system shows that via surveillance tactics that exploit people's labor for promotional gains, enforce normative classification schemes, and culminate in normative cultural productions, Netflix engenders practices that regulate bodies and culture in ways that exemplify interconnections between people, machines, and social institutions.
Tip of the Tongue Known-Item Retrieval: A Case Study in Movie Identification
This work analyzes how searchers express their information needs during tip of the tongue (TOT) known-item retrieval in the movie domain and believes that searchers in TOT states may require specialized query understanding methods or document representations.
Tip of the Tongue Known-Item Retrieval
This work analyzes how searchers express their information needs during tip of the Tongue known-item retrieval states in the movie domain and believes that searchers in TOT states may require specialized query understanding methods or document representations.
Service Marketing Analysis Of Movies As Unique Service-Products
One of the features of films compared to other cultural products is the possibility of their use for advertising and information activities and influence on the formation of needs and audience
Movie Consumption Related Trends And Countertrends In Consumer Behavior
This paper aims to collect and study the various trends related to cultural consumption, more specifically behaviors reflecting in movie related consumption and choice (influencing both the habits of
The use of a smartphone is no doubt increasing, especially in this digitalization era. Younger people mostly use it because they highly rely on online technologies, as a place to get information
Multi-Resolution Attention for Personalized Item Search
This work coupling the conventional multi-head attention module with a differentiable soft-thresholding mechanism, which essentially operates as a masking function in the temporal domain, and captures higher-order temporal relations between user queries and their history across several temporal subspaces.


A taxonomy of web search
This taxonomy of web searches is explored and how global search engines evolved to deal with web-specific needs is discussed.
Analysis of Instant Search Query Logs
The results show that on a people directory search system, instant search can typically save 2 seconds per search, reduce the typing eort by showing the results with fewer characters entered, and increase the success rate.
Recommending for the World
This talk will dive into the problems of uneven availability across catalogs, balancing personal and cultural tastes, handling language, and tracking quality of recommendations, and highlight the four most interesting challenges the Netflix algorithms operate globally encountered.
Impact of response latency on user behavior in web search
A controlled user study tries to understand how users perceive the response latency of a search system and how sensitive they are to increasing delays in response and demonstrates that latency has an impact on the click behavior of users to some extent.
Analysis of a very large web search engine query log
It is shown that web users type in short queries, mostly look at the first 10 results only, and seldom modify the query, suggesting that traditional information retrieval techniques may not work well for answering web search requests.
Rewriting null e-commerce queries to recommend products
This paper describes a system that rewrites null e-commerce queries to find matching products as close to the original query as possible and shows through experiments that high quality product recommendations for more than 25% of null queries are achievable.
Users' music information needs and behaviors: Design implications for music information retrieval systems
A large‐scale user survey questioning various aspects of people's music information needs and behaviors is conducted, and the key findings are presented and 4 emergent themes—(a) the shift in access and use of personal music collections; (b) the growing need for tools to support collaborative music seeking, listening, and sharing; (c) the importance of “visual” music experiences; and (d) the need for ontologies for providing rich contextual information are discussed.
Degenerate Feedback Loops in Recommender Systems
A novel theoretical analysis is provided that examines both the role of user dynamics and the behavior of recommender systems, disentangling the echo chamber from the filter bubble effect, and offers practical solutions to slow down system degeneracy.
Gratifications from using freemium music streaming services: Differences between basic and premium users
Online music streaming services have become popular in listening to music. Most online music streaming services employ the freemium business model. The specific gratifications from online music
2016. Global Languages Support at Netflix
  • 2016