Interpretable Machine Learning Tools: A Survey
Namita Agarwal, Saikat Das
Abstract
In recent years machine learning (ML) systems have been deployed extensively in various domains. But most MLbased frameworks lack transparency. To believe in ML models, an individual needs to understand the reasons behind the ML predictions. In this paper, we provide a survey of open-source software tools that help explore and understand the behavior of the ML models. Also, these tools include a variety of interpretable machine learning methods that assist people with understanding the connection between input and output variables through interpretation, validate the decision of a predictive model to enable lucidity, accountability, and fairness in the algorithmic decision making policies. Furthermore, we provide the state-of-the-art of interpretable machine learning (IML) tools, along with a comparison and a brief discussion of the implementation of those IML tools in various programming languages.