Book Image

Hands-On Recommendation Systems with Python

By : Rounak Banik
Book Image

Hands-On Recommendation Systems with Python

By: Rounak Banik

Overview of this book

Recommendation systems are at the heart of almost every internet business today; from Facebook to Net?ix to Amazon. Providing good recommendations, whether it's friends, movies, or groceries, goes a long way in defining user experience and enticing your customers to use your platform. This book shows you how to do just that. You will learn about the different kinds of recommenders used in the industry and see how to build them from scratch using Python. No need to wade through tons of machine learning theory—you'll get started with building and learning about recommenders as quickly as possible.. In this book, you will build an IMDB Top 250 clone, a content-based engine that works on movie metadata. You'll use collaborative filters to make use of customer behavior data, and a Hybrid Recommender that incorporates content based and collaborative filtering techniques  With this book, all you need to get started with building recommendation systems is a familiarity with Python, and by the time you're fnished, you will have a great grasp of how recommenders work and be in a strong position to apply the techniques that you will learn to your own problem domains.
Table of Contents (9 chapters)

Suggestions for improvements

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 list. There was, however, no justification for doing so. In fact, it is entirely possible that certain keywords appeared in only...