Wrap up

1. Wrap up

Congratulations! You have reached the end of this course on recommendation engines. Let's review what you have learned.

2. Non-personalized models

In chapter 1, you learned what recommendation engines are and how they can be used, and explored how even very basic, non-personalized models can be useful for things like recommending items that have been bought together.

3. Content-based models

In chapter two, you progressed to content-based modeling and learned how it is valuable in cases where you have a lot of information about the items you want to recommend, but maybe not as much about the users in your data.

4. Collaborative filtering

Then in Chapter 3, you moved from knowing a lot about our items to instead having a good understanding of what users liked what, and used collaborative filtering to find new items that would be of interest to our users.

5. Matrix factorization

Finally, in Chapter 4 you learned about how matrix factorization can be used on very sparse datasets, a likely occurrence in real data, to not only generate recommendations but also to learn more about your data using latent features.

6. Congratulations!

Well done, you are now in the position to begin creating your own recommendation engines using your own data! Good luck!

Create Your Free Account

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.