Netflix is a media service based in America in the state of California. It provides services globally, with users from190 different countries. The platform has 137.1 million users, more than 50% of which are from outside the US.

We explore Netflix as a socio-technical system which influences audience preferences and the entertainment industry.  Our analysis focuses on the process of how the algorithm tailors recommendations for users precisely based on individual taste. Additionally, we also studied the impact of the Netflix recommendation system on the media and entertainment industry, how this technology impacts a user’s freedom of choice, and concerns regarding privacy protection.

 

For our technical artifact, we chose to focus on the system architecture of the Netflix recommendation system. The architecture is extremely crucial in being able to understand how the Netflix recommendation is properly utilizing captured user data in order to personalize their recommendation results and curate these results to the users in the best way possible. Additionally the architecture needs to process, store and identify similar patterns amongst users in order to recommend similar items that users would prefer to watch after identifying user taste preferences and viewing patterns. There are four layers that go into the recommendation system. These are the database, algorithm, function and user interaction layers. We dissect the system architecture in presenting all the present elements which lead to shaping the recommendation system.

 

If you wish to learn more about our team members, you can do so here. If you are curious about our technical poster, logo, and why we used the colors that we used or the designs we chose, you can read our design justification here. You can view our socio-technical diagram, which illustrates the factors of our system, and our socio-technical analysis here. You can view the diagram and read our analysis of our technical artifact diagram, which analyses the system architecture of the Netflix recommendation system, here. You can view and learn more about the components of our video, which introduces our project and discusses the recommendation system with experts in the field, here. Lastly, you can view all the resources that we used here.