July 2018
Beginner to intermediate
146 pages
3h 39m
English
The content-based recommenders we've built in this chapter are, of course, nowhere near the powerful models used in the industry. There is still plenty of scope for improvement. In this section, I will suggest a few ideas for upgrading the recommenders that you've already built:
Experiment with the number of keywords, genres, and cast: In the model that we built, we considered at most three keywords, genres, and actors for our movies. This was, however, an arbitrary decision. It is a good idea to experiment with the number of these features in order to be considered for the metadata soup.
Come up with more well-defined sub-genres: Our model only considered the first three keywords that appeared in the keywords ...
Read now
Unlock full access