AI Case Study
Netflix reduces customer churn by several percentage points using machine learning to provide personalised video recommendations
Netflix has reduced its customer churn by improving the videos it recommends for users. It does so by using machine learning algorithms to determine recommendations based on past viewing data, as well as suggesting alternatives to videos not found in the Netflix catalogue. The company estimates $1B in savings per year using personalised recommendations.
Consumer Goods And Services
Entertainment And Sports
"There are typically about 40 rows on each homepage (depending on the capabilities of the device), and up to 75 videos per row; these numbers vary somewhat across devices because of hardware and user experience considerations. The videos in a given row typically come from a single algorithm. Genre rows such as Suspenseful Movies are driven by our personalized video ranker (PVR) algorithm. As its name suggests, this algorithm orders the entire catalog of videos (or subsets selected by genre or other filtering) for each member profile in a personalized way... We have also found that shorter-term temporal trends, ranging from a few minutes to perhaps a few days, are powerful predictors of videos that our members will watch, especially when combined with the right dose of personalization, giving us a trending ranker... We also have a Top N video ranker that produces the recommendations in the Top Picks row. The goal of this algorithm is to find the
best few personalized recommendations in the entire catalog for each member... In general, our different video ranking algorithms use different mathematical and statistical models, different signals and data as input, and require different model trainings designed for the specific purpose each ranker serves."
"Members frequently search for videos, actors, or genres in our catalog; we leverage information retrieval and related techniques to find the relevant videos and display them to our members. However, because members also often search for videos, actors, or genres that are not in our catalog or for general concepts, even search turns into a recommendation problem. In such cases, search recommends videos for a given query as alternative results for a failed search. The extreme crudeness of text input on a TV screen means that interpreting partial queries of two or three letters in the context of what we know about the searching member’s taste is also especially important for us. Our recommender system is used on most screens of the Netflix product beyond the homepage, and in total influences choice for about 80% of hours streamed at Netflix. The remaining 20% comes from search, which requires its own set of algorithms".
According to Netflix: "Our subscriber monthly churn is in the low single-digits, and much of that is due to payment failure, rather than an explicit subscriber choice to cancel service. Over years of development of personalization and recommendations, we have reduced churn by several percentage points. Reduction of monthly churn both increases the lifetime value of an existing subscriber, and reduces the number of new subscribers we need to acquire to replace cancelled members. We think the combined effect of personalization and recommendations save us more than $1B per year".
In-house: "Each of the algorithms in our recommender system relies on statistical and machine learning techniques. This includes both supervised (classification, regression) and unsupervised
approaches (dimensionality reduction through clustering or compression, e.g., through topic models)".
User viewing history