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

The mission

We've all heard the stereotypes: firstborns are very responsible and bossy; the youngest is spoiled and carefree; and the middle child is a jealous introvert! It turns out prominent psychology researchers have reached out to your data science consultancy firm and have conducted several small empirical studies on how birth order affects personality. But they just got a hold of a dataset of over 40,000 online quiz entries from the Open-Source Psychometrics Project. They are skeptical because it was submitted online and they have never conducted a study of that magnitude, so it's uncharted territory. For these reasons, they would like a third party who is well versed in machine learning to approach the problem with fresh eyes. What they hope to learn is about any relation between the quiz answers and the birth order, and also to determine if there are any questions they could use in their empirical studies, or even if online quizzes are a reliable method to begin...