Interpretable Machine Learning with Python

□ I. THÔNG TIN SẢN PHẨM
□ Mã sản phẩm : STT1778
□ Nhà xuất bản : Packt Publishing
□ Tác giả : Serg Masís
□ Ngôn ngữ : Tiếng Anh
□ ISBN : 9781800203907
□ Số trang : 736 trang
□ Hình thức : Bìa Mềm, RUỘT IN ĐEN TRẮNG, BÌA IN MẪU LASER GIẤY C300 CÓ CÁN
□ Loại : Sách gia công đóng gáy keo chắc chắn chất lượng cao
□ Giấy in : Giấy ngoại định lượng 70msg, viết vẽ và highlight thoải mái.
□ Chất lượng : Bản in rõ nét, giá rất tốt cho mọi người.

□ II. MÔ TẢ SẢN PHẨM
□ 1.Mô tả sản phẩm đầy đủ
Interpretable Machine Learning with Python by Serg Masís is a comprehensive guide designed to help data scientists and machine learning engineers move beyond 'black-box' modeling and into the realm of transparent, accountable AI. As machine learning models increasingly automate high-stakes decisions in sectors like healthcare, finance, and law, the need to understand why a model makes a specific prediction has never been more critical. This book provides the practical tools and theoretical foundations necessary to build, interpret, and trust complex models using the Python programming language.

The book is structured into three primary sections. The first section introduces the core concepts of interpretability and explainability, highlighting their business relevance and the ethical implications of 'opaque' AI. It covers 'white-box' models—such as linear regression, logistic regression, and decision trees—that are naturally easy to understand, providing a baseline for more complex techniques. The second section focuses on model-agnostic interpretation methods, which are essential for explaining sophisticated algorithms like Gradient Boosting Machines (GBMs) and Deep Neural Networks. Readers will gain hands-on experience with industry-standard tools including SHAP (SHapley Additive exPlanations), LIME (Local Interpretable Model-agnostic Explanations), and Partial Dependence Plots (PDPs).

The final section of the book addresses the practical challenges of deploying interpretable systems in the real world. Masís delves into advanced topics such as detecting and mitigating algorithmic bias, ensuring adversarial robustness, and utilizing monotonic constraints to guarantee that models behave predictably and safely. Through a variety of hands-on examples—ranging from predicting flight delays to assessing recidivism risk—the book demonstrates how to apply these techniques to tabular data, images, and text. By the end of this guide, practitioners will be equipped to build high-performance models that are not only accurate but also fair, reliable, and easy to explain to stakeholders, effectively bridging the gap between data science and responsible decision-making.

□ 2. Tác giả
Serg Masís has been at the confluence of the internet, application development, and analytics for the last two decades. Currently, he is a Climate and Agronomic Data Scientist at Syngenta, a leading agribusiness company with a mission to improve global food security. Before that role, he co-founded a search engine startup incubated by Harvard Innovation Labs, combining the power of cloud computing and machine learning with principles in decision-making science to expose users to new places and events efficiently. Whether it pertains to leisure activities, plant diseases, or customer lifetime value, Serg is passionate about providing the often-missing link between data and decision-making, and machine learning interpretation helps bridge this gap more robustly.