“Because you watched” by Netflix!



The biggest video streaming giant in the world – Netflix, has a feature of recommending TV shows or movies based on what genres you and the others have watched. Statistics show that eighty percent of the shows watched on Netflix, in the last two years were a result of its own suggestions.

Currently I am watching the recently released Blacklist’s Season 7 and Netflix has already recommended a list to me saying – ‘because I watched Blacklist, I must watch West Wing, Criminal UK, Bloodline, Peaky Blinders etc.’ Cool! isn’t it?

Question: So how do you think Netflix knows? What is this Miss. Know it all algorithm?

Answer: It is called a recommendation/recommender system which works on the principal of Collaborative Filtering.

Collaborative Filtering makes automatic predictions (filtering) about the interests of a user by collecting information from many similar users (collaborating).

For example, If User A is watching Gilmore Girls and User B, C and D have watched Gilmore Girls, New Girl, Baby Daddy, Gossip Girls, Arrested Development and Kim’s Convenience. Netflix will humbly suggest User A to watch the other family dramas mentioned above, after watching Gilmore Girls.

Collaborative filtering saves a user’s time and offers variety but also has some limitations. A new movie or TV show will likely not get recommended till it has a fair share of viewership. It might also happen so that a user has watched a show and did not like it. But just based on the viewing it is suggested several shows of the sorts. For example, I hate Science Fiction, I accidentally watched 2 minutes of Flash and now I keep getting asked to watch Arrow, Legends, Super Girl, Iron Fist, Avatar, Daredevil etc.

In spite of its meagre limitations, I think Collaborative Filtering has added definite value to the whole video streaming experience on Netflix. In a world of extreme customization where in the home appliances, study courses, gadgets like phones and watches, cars, furniture, flooring etc. everything is customizable, it is comfortable as well as commendable to enjoy such sophistication in our digital entertainment service as well.

********************

22 views0 comments

Recent Posts

See All

Text Summarization through use of Spacy library

Text summarization in NLP means telling a long story in short with a limited number of words and convey an important message in brief. There can be many strategies to make the large message short and

 

© Numpy Ninja.