Machine Learning and AI Foundations: Recommendations
58mIntermediate2017-04-10
Authors
Adam Geitgey
Developer and Machine Learning Consultant
Course details
This project-based course shows programmers of all skill levels how to use machine learning to build programs that can make recommendations. In this course, Adam Geitgey walks you through a hands-on lab building a recommendation system that is able to suggest similar products to customers based on past products they have reviewed or purchased. The system can also identify which products are similar to each other.
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.
Learning objectives
Building a machine learning system
Training a machine learning system
Refining the accuracy of the machine learning system
Evaluating the recommendations received
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.
Learning objectives
Building a machine learning system
Training a machine learning system
Refining the accuracy of the machine learning system
Evaluating the recommendations received
Skills covered
scikit-learnMachine LearningArtificial Intelligence FoundationsPythonEssential TrainingArtificial Intelligence (AI)Open Source
Concepts
0. Introduction
- 01 - Welcome
- 02 - What you should know before watching this course
- 03 - Using the exercise files
- 04 - Set up environment
1. The Basics of Making Recommendations
- 05 - What is a recommendation system
- 06 - What can you do with recommendation systems
- 07 - Cool uses of recommendation systems
2. Ways of Making Recommendations
- 08 - Content-based recommendations - Recommending based on product attributes
- 09 - Collaborative filtering - Recommending based on similar users
3. Getting to Know Our Tools
- 10 - Introduction to NumPy, SciPy, and pandas
- 11 - Think in vectors - How to work with large data sets efficiently
4. Building the Framework for Our Recommendation System
- 12 - Explore our product recommendation data set
- 13 - Represent product reviews as a matrix
- 14 - Recommend by predicting missing user ratings
- 15 - A simple way to predict missing user ratings
5. Collaborative Filtering with Matrix Factorization
- 16 - Latent representations of users and products
- 17 - Code the recommendation system
- 18 - How matrix factorization works
- 19 - Use latent representations to find similar products
6. Testing Our System
- 20 - Explore our system s recommendations
- 21 - Use regularization
- 22 - Measure recommendation accuracy
7. Using the Recommendation System in a Real World Program
- 23 - Make recommendations for existing users
- 24 - How to handle first-time users
- 25 - Find similar products
Conclusion
- 26 - Wrap up