PyCon CZ

PyCon CZ 23
15–17 September

Unlocking the Black Box: A practical guide to finding an alibi for your machine learning models a workshop with Ramon Perez

Sunday 17 September 10:00 (7 hours)
Room 303

In the era of complex and powerful machine learning (ML) models, understanding the decision-making process of these models has become more challenging, and different interpretability methods can help us build trust, address bias, and ensure compliance with different standards. The Alibi Explain library offers a comprehensive toolkit for interpreting machine learning models and shed light on their inner workings. No prior experience with the library is required, but some knowledge of machine learning is expected.

During the workshop, we will cover the fundamental concepts and techniques of interpretable machine learning, exploring various explainability methods supported by Alibi Explain. We will discuss techniques such as rule-based explanations, feature importance, and counterfactual explanations. Through hands-on exercises, participants will gain practical experience in interpreting models and understanding their predictions.

Throughout the workshop, we will emphasize real-world applications and use cases to demonstrate the relevance and importance of interpretable machine learning. We will discuss how interpretability can enable better decision-making in domains like finance, healthcare, and retail. By the end of the workshop, attendees will have a good understanding of interpretable machine learning concepts and practical skills for finding an alibi for their ML models.


A laptop.

Attendees should be comfortable with loops, functions, lists comprehensions, and if-else statements.

Attendees need at least 5 GB of free space available.

Good To Have

While it is not necessary to have any knowledge of data analytics or machine learning-related libraries, some experience with pandas, NumPy, scikit-learn, and matplotlib would be very beneficial.

While it is not required to have experience with integrated development environments like VS Code or Jupyter Lab, having either of the two, plus miniconda installed, would be very beneficial for the session.

What do you need to know to enjoy this workshop

Python level

Medium knowledge: You use frameworks and third-party libraries.

About the topic

No previous knowledge of the topic is required, basic concepts will be explained.

Ramon Perez

Hello! I'm Ramon, a data scientist, researcher, and educator living in Sydney. I currently work as a freelance data professional and was previously a Senior Product Developer at Decoded, a technology education company based in the UK. While at Decoded, I created custom data science tools, workshops, and training programs for clients in industries ranging from retail to finance. Prior to that, I held roles at the intersection of education, data science, and research in the areas of entrepreneurship and strategy, alongside a few ventures in consumer behavior and development economics research in industry and academia, respectively. On the personal side, I enjoy giving talks and technical workshops and have had the privilege of participating in several conferences such PyCon, SciPy, PyData, and countless meetup events. In my spare time, I spend as much time as possible mountain biking and exploring many of the outdoor wonders Australia has to offer.