TY - BOOK TI - Interpretable Machine Learning AU - Molnar, Christoph AB - Molnar’s book is about making machine learning models and their decisions interpretable. After exploring the concepts of interpretability, he informs the reader about simple, interpretable models such as decision trees, decision rules and linear regression. Later chapters focus on general model-agnostic methods for interpreting black box models like feature importance and accumulated local effects and explaining individual predictions with Shapley values and LIME. All interpretation methods are explained in depth and discussed critically. Molnar’s book helps the reader to select and correctly apply the interpretation method that is most suitable for your machine learning project. DA - 2019/// PY - 2019 LA - en PB - Christoph Molnar UR - https://christophm.github.io/interpretable-ml-book/ Y2 - 2019/06/23/00:00:00 KW - Interpretability and explainability KW - Machine learning ER -