As a subset of AI, machine learning leaves very few things untouched. Almost every domain that uses technology, finds itself using machine learning. Every company tries to retain their customers and estimates a budget that its algorithms will produce approx. $1billion a year same on Netflix very recommended video will see was selected by algorithms and here Machine Learning is used to improve the quality at Netflix.
Netflix streams to over 117 Million members across the globe and thus providing a good quality response to the customer is a technical challenge for the Netflix. On a Netflix screen, the user is able to view 40 rows of video categories, with each row containing up to 75 videos, according to the paper, which was published in the Dec. 2015 issue of ACM Transactions on Management Information Systems (TMIS).
According to the author Carlos A. Gomez-Uribe and Neil Hunt of Netflix if we offer many choices to the user and we expect that this huge selection will keep viewers to engage in browsing then we are wrong because a viewer loses internet after 60 to 90 seconds of continuous trying to find a video to watch. Like other stores Netflix also has very little time to gain the customers attention so the trendy options should be kept on top rather than many options so all this activity should be prioritize. The training and evaluation of algorithms takes place offline, while A/B testing takes place online.
Historically, Netflix trusted heavily on the ratings given by customers for videos when shipping DVDs by mail. But now Netflix has access to a much large set of data which each member watches, when they watch, the place on the Netflix screen the customer found the video, recommendations the customer didn't choose, and the popularity of videos in the catalog. All the data gets fed into many algorithms power-driven by statistical and machine learning techniques. This approach uses both approaches like supervised and unsupervised. Supervised approach includes classification and regression while unsupervised approach includes reduction through clustering or compression.
A video-to-video similarity algorithm, or Sims, makes recommendations in the "Because You Watched" row. A personalized video ranker algorithm, or PVR, selects the order of videos in genre rows, using an arbitrary subset of the Netflix catalog. As Gomez-Uribe told Wired, "The closer to the first position on a row a title is, the more likely it will get played." But PVR works better when it's mixed with "unpersonalized popularity," he and Hunt wrote in their paper.
As an example, the authors describe recommendations for shows similar to "House of Cards." While one might think that political or business dramas such as "The West Wing" or "Mad Men" would increase customer engagement, it turns out that popular but outside-of-genre titles such as "Parks and Recreation" and "Orange Is the New Black" fared better. The authors call this a case of "intuition failure."
Another algorithm is the "Top N ranker," which makes recommendations in the "Top Picks" row. A Trending Now row uses short-term trends, such as an interest in holiday movies or films driven by weather events.
These short-term trends are powerful predictors of videos that our members will watch, especially when combined with the right dose of personalization. The paper which was published also described that how Netflix uses evidence algorithms which basically focus on that what information we have to show to the viewers about the movies and search algorithms finds that how Netflix performs A/B testing on algorithms and opportunities for rectifying the testing. Thus, machine learning is used to improve the quality at Netflix.