Recommendation Systems: A Practical Hands-On Introduction

Course details

Recommendation systems are among the most profitable artificial intelligence solutions you can deploy, for the simple fact that they can understand what people want amid a seemingly endless number of options. Anytime you buy—or browse—online, there are probably recommendation systems at work presenting you with options at each step. In this course, Miguel González-Fierro teaches some of the techniques used for building, deploying, and testing recommenders. He offers practical, real-world examples to show how you can make a direct impact with recommendation systems, whether you’re a data scientist, machine learning engineer, data engineer, software engineer, or data analyst. Join Miguel in this course to get started building your first recommender and see how high it can boost your metrics.

Concepts

0. Introduction

01 - Why recommendation systems

1. Data Prep

02 - Data in recommendation systems
03 - Data splitting
04 - The cold start problem
05 - Coding - Data prep

2. Modeling

06 - Recommendation systems algorithms
07 - Collaborative filtering
08 - Content-based filtering
09 - Building your first collaborative filtering solution
10 - Building your first content-based filtering solution
11 - Evaluation of recommendation systems
12 - Coding - Collaborative filtering algorithm
13 - Coding - Content-based filtering algorithm

3. Deployment

14 - Recommendation system architectures
15 - Evaluation in production
16 - Coding - Batch architecture

4. MLOps

17 - Tests in recommendation systems
18 - The machine learning lifecycle
19 - Coding - Tests with GitHub actions

Conclusion

20 - Continuing on with recommendation systems

Recommendation Systems: A Practical Hands-On Introduction

Authors

Miguel González-Fierro