Interpretable Machine Learning
Interpretable Machine Learning
Interpretable Machine Learning

This book is 82% complete

Last updated on 2018-08-14

About the Book

"Thank you @ChristophMolnar for the great work on #MachineLearning Interpretability!" - @HJDLopes

"Book on interpretability of ML models, such an important topic often neglected" - @prdeepakbabu

"New book on interpretable #AI by @ChristophMolnar very much needed!" - @AjitJaokar

Machine learning has a huge potential to improve products, processes and research. But machines usually don’t give an explanation for their predictions, which creates a barrier for the adoption of machine learning. This book is about making machine learning models and their decisions interpretable, with a focus on supervised machine learning and tabular data.

After exploring the concepts of interpretability, you will learn about simple, interpretable models and how to interpret them. The later chapters focus on general model-agnostic tools for analysing complex models and making their decisions interpretable. In an ideal future, machines will be able to explain their decisions and the algorithmic age we are moving towards will be as human as possible.

This book is recommended to machine learning practitioners, data scientists, statisticians and anyone else interested in making machine decisions more human.

A free HTML version of the book can be found at:

Table of Contents

  • Introduction
    • Storytime
    • What Is Machine Learning?
    • Definitions
  • Interpretability
    • The Importance of Interpretability
    • Criteria for Interpretability Methods
    • Scope of Interpretability
    • Evaluating Interpretability
    • Human-friendly Explanations
  • Datasets
    • Bike Sharing Counts (Regression)
    • YouTube Spam Comments (Text Classification)
    • Risk Factors for Cervical Cancer (Classification)
  • Interpretable Models
    • Linear Model
    • Logistic Regression
    • Decision Tree
    • Decision Rules (IF-THEN)
    • RuleFit
    • Other Interpretable Models
  • Model-Agnostic Methods
    • Partial Dependence Plot (PDP)
    • Individual Conditional Expectation (ICE)
    • Feature Interaction
    • Feature Importance
    • Global Surrogate Models
    • Local Surrogate Models (LIME)
    • Shapley Value Explanations
  • Example-based explanations
    • Counterfactual explanations
    • Adversarial Examples
    • Prototypes and Criticisms
    • Influential Instances
  • A Look into the Crystal Ball
    • The Future of Machine Learning
    • The Future of Interpretability
  • Contribute
  • Citation
  • Acknowledgements
  • Notes

About the Author

Christoph Molnar
Christoph Molnar

On a mission to make algorithms more interpretable by combining machine learning and statistics.

About the Contributors


Cover designer

The Leanpub 45-day 100% Happiness Guarantee

Within 45 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

See full terms...

Write and Publish on Leanpub

Authors and publishers use Leanpub to publish amazing in-progress and completed ebooks, just like this one. You can use Leanpub to write, publish and sell your book as well! Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks. Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. It really is that easy.

Learn more about writing on Leanpub