Netflix Needs Analytics?

We live in a society of instant gratification. Netflix feeds the fire by offering instant movies streaming to your computer or television. No need to wait for movies in the mail. Another feature that is often talked about is the viewer recommendation system.

Netflix monitors data on viewing habits and is able to create a list of movies, that according to data analysis, shows you will like. Netflix has said it needs to make its recommendation system better. As Netflix’s computer analytics software learns more about each subscriber, the suggestions aim for even narrower targets and better recommendations as a whole.

Netflix executives said they are building on the system. Currently they have approximately 13 years of data to run through to help determine what movies are best suited to certain types of people. The better the recommendation system, the happier the customer. Netflix claims that 2/3rds of the instant views by subscribers is based off of recommendations. This makes it all the more important to ensure the analytics used in determining what viewers might like are accurate.

The goal now is to learn individual viewing preferences so well that every recommendation is a hit with that subscriber, says Ciancutti, Netflix’s vice president of product engineering. The idea behind the recommendation system is to keep viewers inundated with “new” unseen movies so they are not forced to search out videos of their choosing.

Netflix has a limited offering of streamable movies, so the key is to keep customers from looking for specific movies. Instead keep them happy with what is available. “The signals we are getting about what people are watching, when they are watching and how much they are watching are much richer than ever before,” says Neil Hunt, Netflix’s chief product officer. Even if customers do not want to take the time to rate a movie, Netflix can help determine if they liked the movie or not. Did they watch multiple episodes of a television series, did they stop half-way through and never finish it. If they watched multiple episodes this most likely means they like the show, if they stop halfway through and never watch it again, they probably didn’t care for the movie or show.

Using analytics, Netflix hopes to better be able to understand consumer viewing habits and truly offer a recommendation system like none other available. Imagine being able to rely on the recommendations and never have to search out reviews for movies again. Netflix’s use of analytics could be a movie lover’s dream come true.

One comment on “Netflix Needs Analytics?

  1. With 900 ratings you shluod be getting recommendations with AVERAGE dedviation of less than one star from your actual rating of the recommended movies.Why don’t you try the following test: watch any 10 movies but DON’T rate them on Netflix yet, but do write down your rating for each one of them on a paper.Now go to Netflix, run a search for these movies and calculate the average difference between what you rated and what Netflix engine thinks you would rate them. You will be surprised to see that I was right.Brian the recommender engine does not work by actor or genre. It is not as simple as that. If you put some effort into studying the math behind the recommending algorithms, you may change your mind about their capabilities and validity.DR(A Netflix-Prize competitor)

Speak Your Mind