Understand model interpretability methods and apply the most suitable one for your machine learning project. This book details the concepts of machine learning interpretability along with different types of explainability algorithms.

You’ll begin by reviewing the theoretical aspects of machine learning interpretability. In the first few sections you’ll learn what interpretability is, what the common properties of interpretability methods are, the general taxonomy for classifying methods into different sections, and how the methods should be assessed in terms of human factors and technical requirements. Using a holistic approach featuring detailed examples, this book also includes quotes from actual business leaders and technical experts to showcase how real life users perceive interpretability and its related methods, goals, stages, and properties.

Progressing through the book, you’ll dive deep into the technical details of the interpretability domain. Starting off with the general frameworks of different types of methods, you’ll use a data set to see how each method generates output with actual code and implementations. These methods are divided into different types based on their explanation frameworks, with some common categories listed as feature importance based methods, rule based methods, saliency maps methods, counterfactuals, and concept attribution. The book concludes by showing how data effects interpretability and some of the pitfalls prevalent when using explainability methods.

What You’ll Learn

• Understand machine learning model interpretability
• Explore the different properties and selection requirements of various interpretability methods
• Review the different types of interpretability methods used in real life by technical experts
• Interpret the output of various methods and understand the underlying problems

Who This Book Is For

Machine learning practitioners, data scientists and statisticians interested in making machine learning models interpretable and explainable; academic students pursuing courses of data science and business analytics.

Table of Contents

Chapter 1: The Evolution of Machine Learning

Chapter 2: Introduction to Model lnterpretability

Chapter 3: Machine Learning lnterpretability Taxonomy

Chapter 4: Common Properties of Explanations Generated by lnterpretability Methods

Chapter 5: Human Factors in Model lnterpretability

Chapter 6: Explainability Facts: A Framework for Systematic Assessment of Explainable Approaches

Chapter 7: Interpretable ML and Explainable ML Differences

Chapter 8: The Framework of Model Explanations

Chapter 9: Feature Importance Methods: Details and Usage Examples

Chapter 10: Detailing Rule-Based Methods

Chapter 11: Detailing Counterfactual Methods

Chapter 12: Detailing Image lnterpretability Methods

Chapter 13: Explaining Text Classification Models

Chapter 14: The Role of Data in lnterpretability

Chapter 15: The Eight Pitfalls of Explainability Methods

About the Authors

With close to 15 years of professional experience, Anirban Nandi specializes in Data Sciences, Business Analytics and Data Engineering spanning across various business verticals, and building teams from grounds up. Following his Masters from JNU in Economics, Anirban started his career at an US based multi-channel retailer and spent more than eight years working on developing in-house products like Customer Personalization, Recommendation System and Search Engine Classifiers. Post that, Anirban became one of the founding Data Sciences and Analytics members for an organization head-quarted in UAE and spent several years building the onshore and offshore team working on Assortment, Inventory, Pricing, Marketing, Ecommerce and Customer analytics solutions. Currently, Anirban is associated with Rakuten India as the Head of Analytics developing Data Sciences and Analytics solutions for the Rakuten Global Ecosystem across different domains of Commerce, FinTech, Telecommunication, etc. He is also involved in building scalable AI products which can support the data driven decision making culture for the Rakuten Global Ecosystem.

Aditya Kumar Pal works as a Lead Data Scientist with Rakuten at their Bangalore office. Aditya has a rich experience of more than 8 years in domain of Data Sciences and Business Analytics. He has worked with more than 50 stakeholders over the past 8 years to solve their problems using data and algorithms across multiple functions such as customer analytics, pricing analytics, assortment analytics and marketing analytics etc. Couple of years back, Aditya developed interest in model explainability after hearing about it in a seminar of Data Sciences and worked continuously since then over a variety of problems to gain expertise in the domain. He learnt all about the various algorithms and used to find a unique way to combine his knowledge of the business domain with explainability to come up with value creating solutions for the stakeholders. Aditya has received multiple awards across all the organization he has worked at, for his work on data sciences and problem solving. His passion to go into the extreme depth of a topic motivated him to consolidate his knowledge on explainability of machine learning algorithms into a textbook so that his learnings can benefit others in the industry. Aditya also takes part in conferences and has spoken across multiple analytics schools and forums as a guest speaker. He also took a part time role of Data Science coach with one of the leading online education platform to guide a batch of 20 students on data sciences. A passionate sports player and a part time artist, Aditya also has immense love for motorcycles and cars and envisions to someday combine his love for Data Sciences with his hobbies. Additionally, Aditya also cares about social causes such as education for underprivileged kids and environmental protection.