Book Image

Interpretable Machine Learning with Python

By : Serg Masís
Book Image

Interpretable Machine Learning with Python

By: Serg Masís

Overview of this book

Do you want to gain a deeper understanding of your models and better mitigate poor prediction risks associated with machine learning interpretation? If so, then Interpretable Machine Learning with Python deserves a place on your bookshelf. We’ll be starting off with the fundamentals of interpretability, its relevance in business, and exploring its key aspects and challenges. As you progress through the chapters, you'll then focus on how white-box models work, compare them to black-box and glass-box models, and examine their trade-off. You’ll also get you up to speed with a vast array of interpretation methods, also known as Explainable AI (XAI) methods, and how to apply them to different use cases, be it for classification or regression, for tabular, time-series, image or text. In addition to the step-by-step code, this book will also help you interpret model outcomes using examples. You’ll get hands-on with tuning models and training data for interpretability by reducing complexity, mitigating bias, placing guardrails, and enhancing reliability. The methods you’ll explore here range from state-of-the-art feature selection and dataset debiasing methods to monotonic constraints and adversarial retraining. By the end of this book, you'll be able to understand ML models better and enhance them through interpretability tuning.
Table of Contents (19 chapters)
Section 1: Introduction to Machine Learning Interpretation
Section 2: Mastering Interpretation Methods
Section 3:Tuning for Interpretability

Learning about Shapley values

Several chapters in this book will revisit one method in particular: SHAP. So, it's best that we get an overview now of the mathematical foundation and the properties behind it. We will do this through a basketball analogy.

Imagine you are blindfolded at a basketball game where a loudspeaker announces whenever a player for your team enters or exits the court or the team scores. The loudspeaker won't tell you who scored and you are blindfolded, so you don't know who scored or who even assisted! They only refer to players by number, and you don't know who they are anyway. They could be good players or bad players. At any given time, your best guess would be that whoever last joined had something to do with the latest outcome, whether good or bad. Therefore, over time you start getting a sense of which players correlate the most with the better results and which have the opposite effect or none at all.

What if we were able to simulate...