Recommendation is Everywhere

Loading...

En provenance du cours de Princeton University

Networks Illustrated: Principles without Calculus

39 notes

Princeton University

Networks Illustrated: Principles without Calculus

39 notes

What makes WiFi faster at home than at a coffee shop? How does Google order its search results from the trillions of webpages on the Internet? Why does Verizon charge $15 for every GB of data we use? Is it really true that we are connected in six social steps or less? These are just a few of the many intriguing questions we can ask about the social and technical networks that form integral parts of our daily lives. This course is about exploring the answers, using a language that anyone can understand. We will focus on fundamental principles like “sharing is hard”, “crowds are wise”, and “network of networks” that have guided the design and sustainability of today’s networks, and summarize the theories behind everything from the social connections we make on platforms like Facebook to the technology upon which these websites run. Unlike other networking courses, the mathematics included here are no more complicated than adding and multiplying numbers. While mathematical details are necessary to fully specify the algorithms and systems we investigate, they are not required to understand the main ideas. We use illustrations, analogies, and anecdotes about networks as pedagogical tools in lieu of detailed equations. Please note that per Princeton University policy, no certificates, credentials or reports are awarded in connection with this course.

À partir de la leçon

Movie Recommendation on Netflix

One of the perks of having a Netflix subscription is getting recommendations of movies to watch. Behind the scenes, Netflix uses powerful algorithms to determine which will be suggested to each person specifically. In this lesson, we will take a look at the main ideas behind these algorithms.

Netflix Timeline5:21

Video Streaming5:19

Recommendation is Everywhere3:24

Netflix Recommendation System5:20

Netflix Prize: Logistics7:38

Netflix Prize: The Competition4:33

Our Example3:48

Raw Average7:13

User-movie Interactions7:00

Baseline Predictor6:57

Cosine Similarity9:18

Similarity Values10:58

Leveraging Similarity8:30

Neighborhood Predictor4:44

Performance of Different Methods3:30

Copy of Cosine Similarity9:18

Rencontrer les enseignants

Christopher Brinton
Lecturer
Electrical Engineering
Mung Chiang
Professor
Electrical Engineering

So there's many aspects to Netflix in terms of a network setting.

one of which is the video streaming system and we'll look at the Internet a

little more in a future lecture and the technical aspect of that, but right now

we're going to focus more on the social networking aspect.

And we're going to focus specifically on how they recommend movies for you to

watch. So how those recommendation schemes work

and so recommendations really kind of a cool thing because it's like we're mind

reading. Right, we're reading your mind to predict

what we think, what movies we think you would like depending upon what you have

rated and so on, and the similarities between what you rated and the movies

that you haven't watched. And and then we make a prediction.

We say we'd think you'd also like this movie, and so when you go onto Netflix

site and you're browsing through movies, for each one you kind of have three

different options. Right?

You can, you can either rate it. Right here we're showing that you can you

know, give it a certain star rating. If you want.

you can add it to a queue if you actually want to watch it.

so, if you wanted to watch this movie, for instance.

You could say, alright put it in this cue.

Whatever, there's different cues that you can have to watch.

Or you can say, you're not interested. Right?

If you click this Not Interested button, that's also very useful feedback to

Netflix. And to say, don't recommend this movie to

me. It might also say, okay, well, those

types of movies you don't want to see, for instance.

And so each of these things that you do, whether it's rating, add into the queue,

or saying you're not interested, all impact the movies that are going to be

recommended to you. And so you're encouraged again, the more

input that you give the better the recommendation method will be for you

specifically. And so this is the idea of recommending

in Netflix where we're recommending movies for you to watch.

Before we move on to talk just about Netflix's recommendation let's bring up a

few other applications where we see recommendation on the Internet.

There's, obviously everywhere this is happening, but just a few notorious

examples. First is YouTube.

YouTube You Tube has a bar where they recommend videos, that they think you

should watch, and the way that they do that is interesting.

They leverage what's called the co-visitation count, which basically

says, I'm going to recommend to you some movies that have also been watched by

other users. And that, that have also watched the same

movie that you've watched, right? So, if you watched a couple movies.

Then other people, they look at the other people who also watched that movie.

And then they'd look at the movies that the other people have watched in the past

24 hours or so. And then they say, okay.

You'll probably like these movies too. on Amazon they recommend products to you.

So they'll say they'll look at the list of products that you've bought, similar

items therof, they'll look at people who have bought the same products as you and

the other products they've bought and they'll try to recommend things for you

to buy. And on Pandora they recommend songs, so

they actually have a bunch of experts that deal with those recommendations.

And you also have a binary up and down, or thumbs up, or thumbs down voting on

Pandora which indicates what songs get recommend to you and influences that

strongly. So for instance, on Amazon, they just

show this recommended to you right here. It's right now recommending a book for

me, which is on networking, front end engineering and for building websites,

which is pretty similar to this course. And then on YouTube, this is just showing

types of videos that they recommend to you based on what you've watched, and.

Now you can see my musical taste. And if you can go onto, YouTube you might

be able to see that they tend to do a pretty good job of recommending videos

that you might want to watch. That's how people tend to get hooked on

YouTube. In the optional reading, again for this

course, we do have a whole other chapter on YouTube as well that we talk about.

some of the other aspects of YouTube. Like spreading of information.

Explorer notre catalogue

Rejoignez-nous gratuitement et obtenez des recommendations, des mises à jour et des offres personnalisées.

Coursera propose un accès universel à la meilleure formation au monde, en partenariat avec des universités et des organisations du plus haut niveau, pour proposer des cours en ligne.

© 2018 Coursera Inc. Tous droits réservés.

Télécharger dans l'App Store

Disponible sur Google Play