Interpreting Machine Learning Models: Learn Model Interpretability and Explainability Methods

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: Introduction to Machine Learning DomainChapter Goal: The book’s opening chapter will talk about the journey of machine learning models and why model interpretability became so important in the recent times. This chapter will also cover some of the basic black box modelling algorithms in brief  Sub-Topics:• Journey of machine learning domain• Journey of machine learning algorithms • Why only reporting accuracy is not enough for models Chapter 2: Introduction to Model InterpretabilityChapter Goal: This chapter will talk about the importance and need of interpretability and how businesses employ model interpretability for their decisionsSub-Topics:• Why is interpretability needed for machine learning models• Motivation behind using model interpretability• Understand social and commercial motivations for machine learning interpretability, fairness, accountability, and transparency• Get a definition of interpretability and learn about the groups leading interpretability research Chapter 3: Machine Learning Interpretability TaxonomyChapter Goal: A machine learning taxonomy is presented in this section. This will be used to characterize the interpretability of various popular machine learning techniques.Sub topics:• Understanding and trust• A scale for interpretability• Global and local interpretability• Model-agnostic and model-specific interpretability Chapter 4: Common Properties of Explanations Generated by Interpretability MethodsChapter goal: The purpose of this chapter to explain readers about evaluation metrics for various interpretability methods. This will help readers understand which methods to choose for specific use cases  Sub topics: • Degree of importance • Stability• Consistency • Certainty• Novelty Chapter 5: Timeline of Model interpretability Methods DiscoveryChapter goal: This chapter will talk about the timeline and will give details about when most common methods of interpretability were discovered Chapter 6: Unified Framework for Model ExplanationsChapter goal: Each method is determined by three choices: how it handles features, what model behavior it analyzes, and how it summarizes feature influence. The chapter will focus in detail about each step and will try to map different methods to each step by giving detailed examplesSub topics1: • Removal based explanations• Summarization based explanations Chapter 7: Different Types of Removal Based ExplanationsChapter goal: This chapter will talk about the different types of removal based methods and how to implement them along with details of examples and Python packages, real life use cases etc.Sub topics: • IME(2009)• IME(2010)• QII• SHAP• KernelSHAP• TreeSHAP• LossSHAP• SAGE• Shapley• Shapley• Permutation• Conditional• Feature• Univariate• L2X• INVASE• LIME• LIME• PredDiff• Occlusion• CXPlain• RISE• MM• MIR• MP• EP• FIDO-CA Chapter 8: Different Types of Summarization Based ExplanationsChapter goal: This chapter will talk about the different types of summarization based methods and how to implement them along with details of examples and python packages, real life use cases etc. Sub topics:• Magie• Anchor• Recursive partitioning• GlocalX Chapter 9: Model Debugging Using Output of the Interpretability MethodsChapter goal: This chapter will help reader understand how to use the output of the interpretability methods and convert those outputs in to a business ready text which can be understood by non tech business teams Chapter 10: Limitation of Popular Methods and Future of Model InterpretabilityChapter goal: Give users a brief understanding of limitations of some commonly used methods and how business teams find it difficult to deploy models even after usage of interpretability methods. The chapter will also touch upon the future advances in the domain of interpretability Chapter 11: Use of Counterfactual Explanations to Better Understand Model Performance and BehaviourChapter goal: This chapter will introduce readers to the concept of counterfactual explanations and will cover both the basics and the advanced explanation of the algorithm. The chapter will also cover some of the advance Counterfactual explanations methods in detailsSub topics:• CounterFactual guided by prototypes• CounterFactual explanations • MOC (Multi Objective Counterfactuals)• DiCE• CEML Chapter 12: Limitations and Future Use of Counterfactual ExplanationsChapter goal: The chapter will be a closing chapter on counterfactual explanations and will talk about the future scope and advancements in the domain of model explainability

About the Author :
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. Anirban's interests include learning about new technologies and disruptive start-ups. In his spare time he loves networking with people. On the personal side, Anirban loves sports, and is a big follower of soccer/football (Argentina and Manchester United are his favorite teams). Email: aninandi1983@gamil.com Linekdln: https://www.linkedin.com/in/anirban-nandi-89a36ab7/ 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. Email – aditya.nitrr@gmail.com Linkedin - https://www.linkedin.com/in/aditya-kumar-pal-1423624a