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

Mission accomplished

The mission was to determine what machine learning could discover from a dataset of 40,000 quiz entries. The psychology researchers wanted to know if they could trust using this data to provide a path forward for their research. They also wanted to know if machine learning interpretation would show them which features and feature values impact the outcome the most.

Using PDPs, we discovered that there were some discrepancies with the distribution of age and birth order, since the proportion of middle children must increase with age. If any modeling exercise is to work in real-world scenarios, the training data must match real-world distributions. All is not all lost, though. You can take corrective measures by balancing these distributions. Significant changes likely have to be made to the data to make it more reliable for research purposes. That being said, since it's an online quiz made anonymously, you can expect lying to be commonplace, so the margin...