Janhvi Bhojwani
McSherry, Frank and Mironov, Ilya. “Differentially Private Recommender Systems: Building Privacy into the Netflix Prize Contenders.” Microsoft Research. Accessed May 04, 2019. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.482.507&rep=rep1&type=pdf
This study analyzes the Netflix recommendation system through the lens of privacy and accuracy. This study uses a formulaic approach in recommending a system of differential privacy which will be positive as it will ensure users privacy while still having a recommendation system that has accurate enough recommendations.
Blattman, Josefina. “Netflix: Binging on the Algorithm.” UX Planet. August 02, 2018. Accessed May 04, 2019. https://uxplanet.org/netflix-binging-on-the-algorithm-a3a74a6c1f59.
This article shares an in depth explanation on what the Netflix recommendation system is and how it works. The article also uses many visual graphics to compliment the points in the piece. Furthermore, it cites several statistics on how many people use the algorithm to make decisions on what to view and shares an analysis of the psychology of the factors that go into the decisions people make on what to watch using the recommendation system. These include the placement of shows in the recommendation on the screen as well as personalized artwork.
Plummer, Libby. “This Is How Netflix’s Top-secret Recommendation System Works.” WIRED. August 21, 2017. Accessed May 04, 2019. https://www.wired.co.uk/article/how-do-netflixs-algorithms-work-machine-learning-helps-to-predict-what-viewers-will-like.
This article dives into the Netflix recommendation system, and particularly breaks down the system so people can understand what it is and how it works. This article discusses implicit and explicit data that is used to categorize users into different taste groups for the algorithm to generate suggestions.
Xiaoman Chen
Davidson, James, Benjamin Liebald, Junning Liu, Palash Nandy, Taylor Van Vleet, Ullas Gargi, Sujoy Gupta, et al. 2010. “The YouTube Video Recommendation System.” In Proceedings of the Fourth ACM Conference on Recommender Systems, 293–296. RecSys ’10. New York, NY, USA: ACM. https://doi.org/10.1145/1864708.1864770.
This article discusses the video recommendation system in use at YouTube by illustrating challenges that system faces and specific solutions. We expect it would generalize some new thoughts regarding how to examine YouTube’s function of personalized video content and apply them to our study upon Netflix’s recommendation system.
“Learning a Personalized Homepage – Netflix TechBlog – Medium.” Accessed May 2, 2019. https://medium.com/netflix-techblog/learning-a-personalized-homepage-aa8ec670359a.
This article explains how Netflix creates a personalized homepage which caters to each member’s taste and allows for a further exploration at the same time. Specifically, it shows the key parts of the personalization approach by figuring out interface design constraints and differences, initial algorithm set-up, personalized page generation, etc.
Business, Seth Fiegerman, CNN. n.d. “Netflix Adds 9 Million Paying Subscribers, but Stock Falls.” CNN. Accessed May 2, 2019. https://www.cnn.com/2019/01/17/media/netflix-earnings-q4/index.html.
This article indicates at the beginning of 2019 Netflix is approaching to 150 million subscribers, most of which are from its international markets. It shows the fourth quarter earnings report of 2018 and further illustrates the price hike’s influence on subscribers’ growth and how Netflix outcompetes other streaming services by improving members’ experience.
Yaolin Chen
Jugovac, Michael, and Dietmar Jannach. 2017. “Interacting with Recommenders—Overview and Research Directions.” ACM Transactions on Interactive Intelligent Systems 7 (3): 1–46. https://doi.org/10.1145/3001837.
This paper discuss the components of recommendation algorithm framework. Overall, the framework have two mechanisms: preference elicitation and result presentation. The preference elicitation refer to the component that record user preference. For example, the feature of rating and like, preference setting interaction dialogues, and personality quizzes, will allow users to express their preference explicitly. The result presentation is more about internal evaluation and optimized. It involves the presentation of result list, collection of user’s feedback, and persuasion of user habits. These two mechanisms interacted with each other. They guarantee the constant optimization and precisely personalization.
Gomez-Uribe, Carlos A., and Neil Hunt. 2015. “The Netflix Recommender System: Algorithms, Business Value, and Innovation.” ACM Transactions on Management Information Systems 6 (4): 1–19. https://doi.org/10.1145/2843948.
Homepage is the main way of Netflix recommendation system to present users with the recommendation. This paper discusses the major algorithms of Netflix recommendation system. The most important three algorithms are: personal video pick, Top video rankers and video-to-video similarity. They compute and analyze user preference setting, user habits, items from similar genres, and user group trends, and produce result shown in the homepage menu.
CNN. 2014. “A Brief History of Netflix.” July 21, 2014. https://www.cnn.com/2014/07/21/showbiz/gallery/netflix-history/index.html.
Founded in 1997, the service of Netflix is to provide online movie renting. Later in 1999, Netflix adapted the first version of unlimited subscription service. The company began the updating of its recommendation in 2006. It announced a $1 million prize for a better recommendation algorithm solution in 2006. A more successful breakthrough happened in 2007, when Netflix switched its business model from DVD renting to streaming.From then on, the streaming service is closely related to the Netflix recommendation system.
Shuojun Dong
Lund, Jeffrey, and Yiu-Kai Ng. “Movie Recommendations Using the Deep Learning Approach.” 2018 IEEE International Conference on Information Reuse and Integration (IRI), 2018. https://ieeexplore.ieee.org/document/8424686.
This article mainly described recommendation systems are an important part of suggesting items especially in streaming services. For streaming movie services like Netflix, recommendation systems are essential for helping users find new movies to enjoy. In this paper, the authors proposed a deep learning approach based on autoencoders to produce a collaborative filtering system which predicts movie ratings for a user based on a large database of ratings from other users.
Hallinan, Blake, and Ted Striphas. “Recommended for You: The Netflix Prize and the Production of Algorithmic Culture.” Accessed January, 2016. https://journals.sagepub.com/doi/pdf/10.1177/1461444814538646.
This article answered the questions of how does algorithmic information processing affect the meaning of the word culture, and, by extension, cultural practice? This article addressed this question by focusing on the Netflix Prize from 2006 to 2016, they were offering US$1m to the first individual or team to boost the accuracy of the company’s existing movie recommendation system by 10%. It also then represents an effort to add depth and dimension to the concept of “algorithmic culture.”
Wang, Cong, Yifeng Zheng, Jianghua Jiang, and Kim Ren. “Toward Privacy-Preserving Personalized Recommendation Services.” Engineering. Accessed February 16, 2018. https://www.sciencedirect.com/science/article/pii/S2095809917303855.
This article described recommendation systems are crucially important for the delivery of personalized services to users. With personalized recommendation services, users can enjoy a variety of targeted recommendations such as movies, books, ads, restaurants, and more. In addition, personalized recommendation services have become extremely effective revenue drivers for online business. It is important to develop practical privacy-preserving techniques to maintain the intelligence of personalized recommendation services while respecting user privacy.
