For instance, you can see here that OverallQual is the feature that has the most impact on the model output. High values (colored in red on the graph above) of OverallQual can increase a property's price by 60,000 and low values can decrease a price by 20,000. Interesting to know if you're in real estate, isn't it? But this is not all of what SHAP can do! SHAP can also explain a single prediction.

Machine learning interpretability and explainable AI concepts are so popular nowadays in data world. Accuracy and interpretability are inversely proportional. Algorithms show high accuracy such as deep learning or gradient boosting machine would have low interpretability. They were totally black boxes. Some industries such as banking have regulations that enforcing you to be explainable.

InterpretML is an open-source Python package which exposes machine learning interpretability algorithms to practitioners and researchers. InterpretML exposes two types of interpretability - glassbox models, which are machine learning models designed for interpretability (ex: linear models, rule lists, generalized additive models), and blackbox explainability techniques for explaining existing systems (ex: Partial Dependence, LIME). The package enables practitioners to easily compare interpretability algorithms by exposing multiple methods under a unified API, and by having a built-in, extensible visualization platform. InterpretML also includes the first implementation of the Explainable Boosting Machine, a powerful, interpretable, glassbox model that can be as accurate as many blackbox models. The MIT licensed source code can be downloaded from github.com/microsoft/interpret.

This is the second part of our series about Machine Learning interpretability. We want to describe LIME (Local Interpretable Model-Agnostic Explanations), a popular technique to explain blackbox models. It was proposed by Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin in their paper Why Should I Trust You? Explaining the Predictions of Any Classifier, which they first presented at the ACM's Conference on Knowledge Discovery and Data Mining in 2016. Please check out our previous article if you are not familiar with the concept of interpretability. We previously made a distinction between model-specific and model-agnostic techniques as well as between global and local techniques.

Machine learning has a great potential to improve data products and business processes. It is used to propose products and news articles that we might be interested in as well as to steer autonomous vehicles and to challenge human experts in non-trivial games. Although machine learning models perform extraordinary well in solving those tasks, we need to be aware of the latent risks that arise through inadvertently encoding bias, responsible for discriminating individuals and strengthening preconceptions, or mistakenly taking random correlation for causation. In her book „Weapons of Math Destruction", Cathy O'Neil even went so far as to say that improvident use of algorithms can perpetuate inequality and threaten democracy. Filter bubbles, racist chat bots, and foolable face detection are prominent examples of malicious outcomes of learning algorithms. With great power comes great responsibility--wise words that every practitioner should keep in mind.

Navdeep Gill is a Software Engineer & Data Scientist at H2O.ai where he focuses on model interpretability, GPU accelerated machine learning, and automated machine learning. He graduated from California State University, East Bay with a M.S. degree in Computational Statistics, B.S. in Statistics, and a B.A. in Psychology (minor in Mathematics). During his education, he gained interests in machine learning, time series analysis, statistical computing, data mining, and data visualization. Before joining H2O.ai, he worked at Cisco Systems, focusing on data science and software development. Before stepping into industry he worked in various Neuroscience labs as a researcher/analyst.

Ready to take the next step with ML? Check out these recommended resources from O'Reilly's editors. Hands-On Machine Learning with Scikit-Learn and TensorFlow -- Using concrete examples, minimal theory, and two production-ready Python frameworks, author Aurélien Géron helps you gain an intuitive understanding of the concepts and tools for building intelligent systems. Sprouted Clams and Stanky Bean: When Machine Learning Makes Mistakes -- Janelle Shane shows how machine learning mistakes can be embarrassing or even dangerous.

The last decade has seen huge progress in the development of advanced machine learning models; however, those models are powerless unless human users can interpret them. Here we show how the mind's construction of concepts and meaning can be used to create more interpretable machine learning models. By proposing a novel method of classifying concepts, in terms of 'form' and 'function', we elucidate the nature of meaning and offer proposals to improve model understandability. As machine learning begins to permeate daily life, interpretable models may serve as a bridge between domain-expert authors and non-expert users.