- Basic concepts: Introduction to Machine Learning (32 pg taken from my book) and Reasons why ML can fail (12 pg)
- Use case: step-by-step tutorial to improving retention with churn prediction (15 pg)
- Framework: the unique Machine Learning Canvas and its guide to formalize your own use cases
- Hands-on: curated datasets to experiment with, Python environment and notebooks, Docker image
Last update on January 8, 2017
The email course (optional)
More free content to get you started with ML progressively:
- 8 bite-sized pieces delivered to your inbox over 30 days
- Summarized excerpts from my book: example use cases of ML, how to formalize your own use case, data preparation, tips to create value from data, etc.
- Links to bonus material: videos of presentations, hands-on demos, and some of my most popular articles to read offline.
About the author
My name is Louis Dorard, I'm an independent consultant and my goal is to help people use ML to make their applications and their businesses smarter.
I'm the author of Bootstrapping Machine Learning and I'm the General Chair of PAPIs.io, the 1st series of international conferences dedicated to real-world ML applications, and to the innovations, techniques and tools that power them.
I also teach Predictive Analytics at University College London School of Management.