(Ebook) An Introduction to Machine Learning Interpretability by Patrick Hall and Navdeep Gill ISBN 9781492033141, 1492033146

(Ebook) An Introduction to Machine Learning Interpretability by Patrick Hall and Navdeep Gill ISBN 9781492033141, 1492033146

Understanding and trusting models and their results is a hallmark of good sci‐ence. Scientists, engineers, physicians, researchers, and humans in general havethe need to understand and trust models and modeling results that affect theirwork and their lives. However, the forces of innovation and competition are nowdriving analysts and data scientists to try ever-more complex predictive modelingand machine learning algorithms. Such algorithms for machine learning includegradient-boosted ensembles (GBM), artificial neural networks (ANN), and ran‐dom forests, among many others. Many machine learning algorithms have beenlabeled “black box” models because of their inscrutable inner-workings. Whatmakes these models accurate is what makes their predictions difficult to under‐stand: they are very complex. This is a fundamental trade-off. These algorithmsare typically more accurate for predicting nonlinear, faint, or rare phenomena.Unfortunately, more accuracy almost always comes at the expense of interpreta‐bility, and interpretability is crucial for business adoption, model documentation,regulatory oversight, and human acceptance and trust.