You're reading from The Machine Learning Solutions Architect Handbook Practical strategies and best practices on the ML lifecycle, system design, MLOps, and generative AI

Product type Paperback

Published in Apr 2024

Publisher Packt

ISBN-13 9781805122500

Length 602 pages

Edition 2nd Edition

Languages

Python

Tools

MLOps

Concepts

Machine Learning

Author (1):

David Ping

Preface

1. Navigating the ML Lifecycle with ML Solutions Architecture FREE CHAPTER

2. Exploring ML Business Use Cases

3. Exploring ML Algorithms

4. Data Management for ML

5. Exploring Open-Source ML Libraries

6. Kubernetes Container Orchestration Infrastructure Management

7. Open-Source ML Platforms

8. Building a Data Science Environment Using AWS ML Services

9. Designing an Enterprise ML Architecture with AWS ML Services

10. Advanced ML Engineering

11. Building ML Solutions with AWS AI Services

12. AI Risk Management

13. Bias, Explainability, Privacy, and Adversarial Attacks

14. Charting the Course of Your ML Journey

15. Navigating the Generative AI Project Lifecycle

16. Designing Generative AI Platforms and Solutions

17. Other Books You May Enjoy

18. Index

Understanding ML explainability

There are two main concepts when it comes to explaining the behaviors of an ML model:

Global explainability: This is the overall behavior of a model across all data points used for model training and/or prediction. This helps to understand collectively how different input features affect the outcome of model predictions. For example, after training an ML model for credit scoring, it is determined that income is the most important feature in predicting high credit scores across data points for all loan applicants.
Local explainability: This is the behavior of a model for a single data point (instance), and which features had the most influence on the prediction for a single data point. For example, when you try to explain which features influenced the decision the most for a single loan applicant, it might turn out that education was the most important feature, even though income was the most important feature at the global level.