A Unified Approach to Interpreting Model Predictions

Link: https://papers.nips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf



Understanding why a model makes a certain prediction can be as crucial as the
prediction’s accuracy in many applications. However, the highest accuracy for large
modern datasets is often achieved by complex models that even experts struggle to
interpret, such as ensemble or deep learning models, creating a tension between
accuracy and interpretability. In response, various methods have recently been
proposed to help users interpret the predictions of complex models, but it is often
unclear how these methods are related and when one method is preferable over
another. To address this problem, we present a unified framework for interpreting
predictions, SHAP (SHapley Additive exPlanations). SHAP assigns each feature
an importance value for a particular prediction. Its novel components include: (1)
the identification of a new class of additive feature importance measures, and (2)
theoretical results showing there is a unique solution in this class with a set of
desirable properties. The new class unifies six existing methods, notable because
several recent methods in the class lack the proposed desirable properties. Based
on insights from this unification, we present new methods that show improved
computational performance and/or better consistency with human intuition than
previous approaches.

Author(s): Scott M. Lundberg, Su-In Lee

Publication Date: 2017

Publication Site: Conference on Neural Information Processing Systems

Interpretable Machine Learning: A Guide for Making Black Box Models Explainable

Link: https://christophm.github.io/interpretable-ml-book/



Machine learning has great potential for improving products, processes and research. But computers usually do not explain their predictions which is a barrier to the adoption of machine learning. This book is about making machine learning models and their decisions interpretable.

After exploring the concepts of interpretability, you will learn 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. How do they work under the hood? What are their strengths and weaknesses? How can their outputs be interpreted? This book will enable you to select and correctly apply the interpretation method that is most suitable for your machine learning project.

Author(s): Christoph Molnar

Publication Date: 2021-06-14

Publication Site: github

Idea Behind LIME and SHAP

Link: https://towardsdatascience.com/idea-behind-lime-and-shap-b603d35d34eb



In machine learning, there has been a trade-off between model complexity and model performance. Complex machine learning models e.g. deep learning (that perform better than interpretable models e.g. linear regression) have been treated as black boxes. Research paper by Ribiero et al (2016) titled “Why Should I Trust You” aptly encapsulates the issue with ML black boxes. Model interpretability is a growing field of research. Please read here for the importance of machine interpretability. This blog discusses the idea behind LIME and SHAP.

Author(s): ashutosh nayak

Publication Date: 22 December 2019

Publication Site: Toward Data Science