Providing recommendations and choices like "Top Picks for You," "Similar Titles," "Friends You May Know," and "People Also Bought This" are crucial for cutting through the chaos of web content now available and catching your customers (or potential customers) attention and interest. This training teaches you how to start designing recommendation engines and what you need to consider when you want to bring such algorithms to production. Through instructor-led discussion and interactive, hands-on exercises, you will learn how to design a recommendation architecture that can search, map and provide users with relevant information personalized to preference and taste.
Q: Is Recommendation Engines and Algorithms training right for me?
- Yes - if you have experience with data science using Python
- Yes - if you are proficient with data science tooling (SSH, git, Jupyter Notebook, Numpy, Pandas, Sklearn)
- Yes - if you know the basics of machine learning (ML) and have knowledge of bias versus variance tradeoff, logistic regression, etc
Q: What will I achieve by completing this training?
You will learn:
- Different recommendation algorithms
- How to compare recommenders with proper AB tests
- Common pitfalls and solutions
You will gain hands-on experience in:
- Experimenting with specialized Python libraries for recommendation algorithms
- Setting up an AB test
- Evaluating your different algorithms in a semi-live setting
You will develop the skills to:
- Begin designing recommendation engines for your organization
- Begin designing experiments to optimize your website
Q: What else should I know?
Minimum one-year working experience with Python, either as a data scientist or as a data engineer.
- Please bring a modern laptop with Anaconda, SSH and git installed
- You must also be able to install Python packages on your machine by yourself
- Some of the exercises may require you to set up your virtual environment from the command line