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)
1
Section 1: Introduction to Machine Learning Interpretation
5
Section 2: Mastering Interpretation Methods
12
Section 3:Tuning for Interpretability

Chapter 3: Interpretation Challenges

In this chapter, we will discuss the traditional methods used for machine learning interpretation for both regression and classification. This includes model performance evaluation methods such as RMSE, R-squared, AUC, ROC curves, and the many metrics derived from confusion matrices. We will also explore several dimensionality reduction visualization techniques that can be leveraged for interpretation purposes. We will then examine the limitations of these traditional methods and explain what exactly makes "white-box" models intrinsically interpretable and why we cannot always use white-box models. To answer this question, we'll consider the trade-off between prediction performance and model interpretability. Finally, we will discover some new "glass-box" models such as EBM and skope-rules that attempt to not compromise in this trade-off.

The following are the main topics that will be covered in this chapter:

    ...