There’s no such thing as a ‘@Netflix show.’ That as a mind-set gets people narrowed. Our brand is personalization.” (Ted Sarandos: Chief Content Officer at Netflix)

How Netflix is doing personalization

(Source: https://www.linkedin.com/pulse/how-netflix-uses-ai-data-conquer-world-mario-gavira/)

Netflix’s core competency in data science enables the personalization of the streaming experience based on user behaviour. Netflix classifies and tags content to get a nuanced view of consumer preferences. Netflix has developed over 1,000 tag types that classify content by genre, time period, plot conclusiveness, mood, etc. These tags help to define micro-genres, which, by 2014, had already reached 76,897. Content micro-classification, combined with a proprietary recommendation engine, enables Netflix to serve better customer experience. About 75% – 80% of viewer activity is influenced by the recommendation algorithm

Netflix also tracks viewing habits of its subscriber base from the early beginning and created almost 2000 clusters, so-called “taste communities”.

Traditional TV networks use standard demographic ratings such as age, race or location for their market segmentation. Netflix instead tracks viewing habits of its subscriber base from the early beginning and created almost 2000 clusters, so-called “taste communities”.

The power of recommendations

(Source: https://vibeprojects.com/heres-how-netflix-uses-ai-and-data-to-conquer-the-world/)

Netflix’s Senior Data Scientist, Mohammad Sabah stated in 2014:

“75 percent of users select movies based on the company’s recommendations, and Netflix wants to make that number even higher.”

These recommendations are powered by algorithms that are based on the assumption that similar viewing patterns represent similar user tastes. The taste communities play an instrumental role in these recommendation algorithms. We didn’t come out of the gate and say, ‘We think Black Mirror is for this audience or not for that audience’. But after we launched the show, we were able to see the patterns. The chart showed how folks who liked Black Mirror were also fans of Lost and Groundhog Day. On the surface, if you thought about Groundhog Day with Black Mirror, you might not find an obvious similarity.”

But the recommendation algorithms go beyond the “taste” criterion. Netflix also includes contextual criterion to find the perfect recommendation for each user at each moment.

We have data that suggests that there the viewing behaviour differs depending on the day of the week, the time of day, the device, and sometimes even the location. Most internet companies use batch processing for personalization use cases such as recommendations, but Netflix realized that this was not quick enough for time-sensitive scenarios such as new title launch campaigns or strong trending popularity cases.  They moved to a near-real-time (NRT) recommendation process to accelerate the learning process and roll out test results.

A picture is worth more than a thousand words

Netflix sets themselves apart from traditional media companies not only by what they recommend but how they recommend it to their members. A key feature is an image they use to promote each movie or TV show, or the so-called artworks. Netflix aims to provide the artwork for each show that highlights the specific visual clue that is relevant for each individual member. For each new title, different images are randomly assigned to different subscribers, using the taste communities as an initial guideline. This translates into hundreds of millions of personalized images continuously being tested among its subscriber base. For the creation of the artwork, machine learning also plays a critical role; thanks to a computer vision algorithm that scans the shows and picks the best images that will be tested among the taste communities.

Go beyond standard industry metrics

Netflix does not limit the success or failure of a show to the size of its audience. Shows with a smaller audience but low production costs can also remain profitable. John Ciancutti, former VP of Product Engineering summarised the key criteria for content selection as follows:

Netflix seeks the most efficient content. Efficient here means content that will achieve the maximum happiness per dollar spent. There are various complicated metrics used, but what they are intended to measure is happiness among Netflix members.