Build interest by showing applications of recommendation systems.
- [Instructor] Recommendation systems are behind the scenes in many products that you use everyday. You've probably seen recommendation systems in action on ecommerce websites. When you buy something on Amazon, the next time you visit you will see recommended products based on your purchase. This is powered by a recommendation system. But that's just the tip of the iceberg. Social media websites like Facebook and Instagram rely heavily on recommendation systems. These websites use recommendation systems to decide which post to display in your timeline and which new friends to recommend to you.
Music streaming services rely on recommendation systems to help you discover new music. Spotify uses a recommendation system to generate automatic playlists of music it thinks that you'll enjoy. If you're constantly discovering new artists that you love, you're more likely to keep using the service. Netflix uses a recommendation system to decide which movies and tv shows to present to you. They are famous for their research and recommendation systems. In 2006 they started the Netflix prize which was a contest for the first team that can improve the recommendation accuracy by 10% would win one million dollars.
Three years later the challenge was completed and the prize was awarded. Recommendation systems also pop up in all kinds of other products. Online dating applications use recommendation systems to decide which users to show to each other. Banks and investment companies use recommendation systems to match different accounts and services to users. Insurance companies do the same. The applications for recommendation systems are nearly endless.
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