Understand what a recommendation system is.
- [Narrator] A recommendation system is a computer program that helps a user discover products and content by predicting the user's rating of each item and showing them the items that they would rate highly. Recommendation systems are everywhere. If you've ever looked for books on Amazon or browsed through posts on Facebook, you've used the recommendation system without even knowing it. With online shopping, consumers have nearly infinite choices. No one has enough time to try every product for sale. Recommendation systems play an important role in helping users find products and content they care about without having to spend all their time digging through things they won't like.
Behind the scenes, these systems are powered by a recommender function. A recommender function takes in information about the user and predicts the rating the user would give the product. If you can predict the user's rating for a product before the user even sees the product, that's very powerful. That means you can show the user only the things they would like the best and not waste their time with products they won't care about. Imagine you're browsing for an ebook to buy on your ereader. The online book store knows about your past book purchases and the ratings that you gave them. Based on that historical information, it tries to predict how you will rate every product in its library.
Using these predicted ratings, the book store will show you the books that it thinks you'll enjoy the most. These are also the books that you are most likely to purchase. Recommendation systems enhance the user experience while providing more exposure to a larger part of the company's inventory.
Recommendation systems are a key part of almost every modern consumer website. The systems help drive customer interaction and sales by helping customers discover products and services they might not ever find themselves. The course uses the free, open source tools Python 3.5, pandas, and numpy. By the end of the course, you'll be equipped to use machine learning yourself to solve recommendation problems. What you learn can then be directly applied to your own projects.
- Building a machine learning system
- Training a machine learning system
- Refining the accuracy of the machine learning system
- Evaluating the recommendations received