If you’ve been thinking that Netflix’s system of marketing its hundreds of original movies seem highly calculated, then it’s because they are. Netflix has shown how it uses AI to market shows and predict their success in ways that conventional box office numbers and Nielsen ratings likely couldn’t match.
Although it’s not rocket science, it simply boils down to finding connections and determining the likely audience sizes.
According to Netflix, the method depends on transfer learning, where the parameters learned from a source task improve the performance of a target task. This means, what titles are comparable to a Netflix original, and what kind of viewership can the service attract?
For thematic comparisons, Netflix creates a “similarity map” where AI uses a show’s metadata, tags, and summaries “embeddings” in Netflix’s world to determine links to other titles. That would help Marketers to know which shows and movies to help describe a coming-of-age comedy, for instance.
Then in determining audience sizes, Netflix has an AI model that compares the audience sizes of similar work in a given country. If a drama is likely to fare well in Spain, Netflix might not only ramp up marketing in the region but prepare dubs and subtitles earlier.
The Netflix systems are self-supervised, allowing them to access a much broader range of titles than they would if they were limited to Netflix’s info only.
Though you may not find Netflix’s system thrilling if you prefer the human approach, because there’s nothing quite like an indie production getting a huge audience after an executive takes a chance on it.
The AI approach makes it much easier for Netflix to market a flood of originals and eliminates some of the subjectivity that could hurt the success of some shows and movies.