Book Image

Responsible AI in the Enterprise

By : Adnan Masood, Heather Dawe
5 (1)
Book Image

Responsible AI in the Enterprise

5 (1)
By: Adnan Masood, Heather Dawe

Overview of this book

Responsible AI in the Enterprise is a comprehensive guide to implementing ethical, transparent, and compliant AI systems in an organization. With a focus on understanding key concepts of machine learning models, this book equips you with techniques and algorithms to tackle complex issues such as bias, fairness, and model governance. Throughout the book, you’ll gain an understanding of FairLearn and InterpretML, along with Google What-If Tool, ML Fairness Gym, IBM AI 360 Fairness tool, and Aequitas. You’ll uncover various aspects of responsible AI, including model interpretability, monitoring and management of model drift, and compliance recommendations. You’ll gain practical insights into using AI governance tools to ensure fairness, bias mitigation, explainability, privacy compliance, and privacy in an enterprise setting. Additionally, you’ll explore interpretability toolkits and fairness measures offered by major cloud AI providers like IBM, Amazon, Google, and Microsoft, while discovering how to use FairLearn for fairness assessment and bias mitigation. You’ll also learn to build explainable models using global and local feature summary, local surrogate model, Shapley values, anchors, and counterfactual explanations. By the end of this book, you’ll be well-equipped with tools and techniques to create transparent and accountable machine learning models.
Table of Contents (16 chapters)
Part 1: Bigot in the Machine – A Primer
Part 2: Enterprise Risk Observability Model Governance
Part 3: Explainable AI in Action

Shapley Additive exPlanations

SHapley Additive exPlanations, commonly known as SHAP, is a tool for making ML models more interpretable. It does this by providing explanations for individual predictions, called Shapley values. SHAP values are different from traditional model interpretation methods such as feature importance because they take into account the interactions between features. This makes them more accurate and reliable, especially in complex models.

SHAP works by approximating the value that each feature contributes to a prediction. This is done using a game-theoretic approach, which assigns each feature a score based on its importance in determining the outcome of the game (prediction). The final SHAP value for a given feature is then calculated as the average of all possible ways that feature could have been included in the prediction. SHAP can be used to explain the output of any ML model. Even though this approach was first proposed by game theorists, it has been...