Pretty much everyone is familiar with Netflix. Netflix has what seems like countless tv-shows and movies at its disposal. How do they take this large amount of shows and movies and compact it into recommendations based solely on an individual?
They use Machine learning, algorithms, and creativity to deal with giving great recommendations to their 100 million subscribers
The recommendation system works by putting together data collected from different places. Recommended rows are tailored to your viewing habits.
Systems like Netflix are based on machine learning. They rewrite themselves as they learn from their own users. Every time you press play and spend some time watching a TV show or a movie, Netflix is collecting data that informs the algorithm and refreshes it. The more you watch the more current and accurate the algorithm is. If you do not watch Netflix a lot then the algorithm may not be very good at predicting what you like because it has so little data.
The Netflix experience is driven by a number of machine learning algorithms: ranking, search, similarity, ratings and more. Netflix has to know their users and get recommendations tailored to each individual.
Each viewer fits into multiple groups and these affect what recommendations pop up to the top of each persons screen.
Netflix has actually hired people to categorize TV shows and movies and apply tags to each of them in order to create hyperspecific micro genres such as “Visually-striking nostalgic dramas” or “Understated romantic road trip movies”. This can help their algorithms really narrow down what an individual likes watching.
Chris Alvino, Machine Learning Engineer at Netflix, explains why they choose rows to make it easier for members to navigate through a large portion of their catalog. By presenting coherent groups of videos in a row, providing a meaningful name for each row, and presenting rows in a useful order, members can quickly decide whether a whole set of videos in a row is likely to contain something that they are interested in watching at that precise moment. This allows members to either dive deeper and look for more videos in the theme or to skip them and look at another row.
Netflix has implemented recently a new recommendation algorithm based on artwork.
Netflix says that if they don’t capture a user’s attention within 90 seconds, he or she will likely lose interest and move onto another activity. Having such a short time to capture interest, images becomes the most efficient and compelling way to make users discover the perfect title as quickly as possible.
Netflix has built a system that tests a set of images for many titles on their catalogue helping display a compelling image to drive engagement. Through many experiments and tests, Netflix arrived to the conclusion that seeing a certain range of emotions actually compels people to watch a TV show or movie.
An example of this is seen in the recent winning image (“winning” means it drove the most engagement) for the second season of Unbreakable Kimmy Schmid
Netflix chooses what image they use based on customer preferences