.Net Foundation ML.NET, 23 Sep 2019

Previous Meeting Next Meeting

⏯

youtube image

►

From YouTube: Build a ML model for Movie Recommendation | ML.NET [7 of 8]

Description

Following our last video, here are even more ways to use the model builder with ML.NET. In this video, we learn how to recommend movies for users using colloborative filtering based recommendation approach.

Follow Pranav Rastogi: https://twitter.com/rustd

Watch the entire series here: https://aka.ms/dotnet3-mlnet
Download Visual Studio 2019 here: https://aka.ms/VisualStudio-dotnetconf19
Download .NET Core 3.0 here: https://aka.ms/Dotnet3

Learn more about ML .NET:
Movie recommendation with ML.NET: https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/movie-recommendation?&WT.mc_id=Educationalmlnet-c9-niner
What is Model Builder and how does it work? https://docs.microsoft.com/en-us/dotnet/machine-learning/automate-training-with-model-builder?&WT.mc_id=Educationalmlnet-c9-niner
ML.NET Model Builder: https://dotnet.microsoft.com/apps/machinelearning-ai/ml-dotnet/model-builder?&WT.mc_id=Educationalmlnet-c9-niner
Get started with ML.NET: https://dotnet.microsoft.com/learn/ml-dotnet/get-started-tutorial/intro?&WT.mc_id=Educationalmlnet-c9-niner
GitHub Repo ML .NET: https://github.com/dotnet/machinelearning
GitHub Repo ML.NET Samples: https://github.com/dotnet/machinelearning-samples/blob/master/README.md

Follow us:
 Twitter: https://twitter.com/dotnet
Facebook: https://www.facebook.com/Dotnet/
Blogs: https://devblogs.microsoft.com/dotnet/?WT.mc_id=Educationalmlnet-c9-niner
Shows and Podcasts: https://channel9.msdn.com/Shows/On-NET/?&WT.mc_id=Educationalmlnet-c9-niner

Useful Links:
Learn .NET: https://dotnet.microsoft.com/learn?&WT.mc_id=Educationalmlnet-c9-niner
.NET Community: https://dotnet.microsoft.com/platform/community?&WT.mc_id=Educationalmlnet-c9-niner
.NET Documentation: https://docs.microsoft.com/en-us/dotnet/?&WT.mc_id=Educationalmlnet-c9-niner

A

In this video, we will take a look at how to build a custom machine.

A

Learning model for movie recommendations.

A

Let's go and understand how does movie recommendation.

A

Works and what are the different ways of recommending movies.

A

The most common way of recommending movies is by rating.

A

So, let's assume,, you have a website.

A

Where people can browse and see movies and they can rate all the movies., so the simplest recommendation system is recommend me movies. If the rating is higher than 8,.

A

And so that's one way of recommending movies.

A

The second way of recommending movies is by content based filtering.

A

So this is around movies of certain genre are very popular.

A

So for example, recommend me action movies based on my browsing history. If I.

A

Like a lot of action movies or recommend me superhero movies, if I like a lot of superhero movies.,.

A

The third approach is around collaborative filtering,.

A

Which combines the first two approaches.

A

What this approach comes down to is,.

A

Let's say there are different users who have different browsing or viewing habits.

A

in this case, what's happening here is we have three users, ankit,, gal, and cesar,, and there are three different patterns for heat,.

A

Mission, impossible, and home alone.

A

the question over here: is,: what's the probability of gal liking, home alone?.

A

Collaborative filtering is observing the behaviors.

A

Of users who have common likes and common dislikes.

A

So for example, in this case, we know that cesar likes heat and mission, impossible,.

A

And gal also likes heat and mission impossible.

A

So if cesar and gal have similar viewing habits,.

A

And cesar doesn't like home alone,, then it's more likely that gal also doesn't like home alone.

A

So this is collaborative filtering and this is what we.

A

Can use in our movie recommendation example.

A

Let's understand what the data looks like.

A

For a typical scenario for recommending movies.

A

This is a typical dataset,.

A

Which also becomes your features or your input.

A

To your model, in terms of how do you want to recommend movies.

A

We have user ids,, we have movie ids, and movie names, or movie genres, and ratings, and timestamp,, and this dataset is directly capturing. What.

A

Were the viewing habits of these set of users.

A

Then,, what did they actually like in terms of ratings,.

A

And what did they actually see in terms of movies, which has information around? What was the genre of the movie,.

A

And other characteristics as well.

A

The output or the column that you want to predict,.

A

Or the output of your machine learning model becomes the rating,.

A

Which means,, what's the likelihood of this user liking, the movie or not?, so you're, going to recommend a set of movies to a user based on.

A

Their browsing history or their likes and dislikes using.

A

The collaborative filtering approach that we just saw.

A

Now that we've understood the basics of movie recommendation,.

A

Let's see how movie recommendation model.

A

Can be built and used in your application.

A

So I have two projects in my solution,.

A

One is on how the model was trained,.

A

And the other is a web application where I'm going to use the model..

A

So let's look at the how the model was trained as well.

A

We know that in a typical machine learning, workflow,.

A

The first steps are around loading: your data.

A

So in this case, I have loaded data from my ratings dataset,.

A

Which has the ratings for all the users, along with the movie that they saw and the rating that they gave.

A

I'm going to "featurise" all the values of the movies,.

A

And I'm going to use this as input features., so my user id and movie id are going to become my input. Features.

A

For my training algorithm,, I'm going to use field aware factorization, machine,.

A

Where I'm going to input all the features, and I'm going to train the model., then I'm going to evaluate the model by trying out that model on.

A

A specific user and then seeing what.

A

The top five movies that I can recommend to the user as well.

A

So let's go ahead and run this application. First,.

A

And so, let's launch it.

A

what this will do is it'll load, the dataset,.

A

It will extract all the features,, it will train the model,, evaluate the model, and then try the model as well.

A

So in this case, it evaluated the model with around 60 percent accuracy, and for a user id six with movie id 10,.

A

The probability of me liking movie id is about 45 percent.

A

So that's an example of building a recommendation. Model.

A

Let's switch over to our web application and see this model in practice.

A

So this is asp.net web application.

A

You can imagine that this is your movie site,.

A

Where I have three users, ankit, amy, and cesar.,.

A

If I click ankit,, you can see that this is the browsing history for ankit, where he's watched, heat,.

A

Terminator 2, independence day,- and these are the all time- box-office movies that are popular all up.. So when I click "recommend", what I want to find out is, of all the top box-office movies,.

A

Which are the ones that ankit is most likely to see?.

A

So if I click "recommend",, you would see that there is a 56 percent chance that ankit, like face/off,.

A

88 percent chance that ankit, like casino royale,.

A

And 85 percent chance that ankit might like gladiator.

A

If I go back to my site and switch to.

A

Cesar and recommend movies for cesar, as well,.

A

You will see that cesar has about 70 percent likelihood of flaking gladiator.

A

If you look at how this was built,.

A

I can go over to my movies controller,.

A

And I can go to the recommend action,, where what we're doing over here is. We are loading. The machine learning model that we just built,.

A

And we're calling the prediction engine for that particular user,.

A

And getting the list of movies that the user is going to like,.

A

And we're going to update the view with that particular information as well..

A

So this is how you can start.

A

Incorporating recommendation into your application.

A

So what we saw over here was how to build.

A

A custom machine learning model for movie recommendation.

A

In the next video, we will take a look at how to build a machine learning model for classifying images.