Explaining the output of a complex machine learning (ML) model often requires approximation using a simpler model. To construct interpretable explanations that are also consistent with the original ML model, counterfactual examples --- showing how the model's output changes with small perturbations to the input --- have been proposed. This paper extends the work in counterfactual explanations by addressing the challenge of feasibility of such examples. For explanations of ML models in critical domains such as healthcare, finance, etc, counterfactual examples are useful for an end-user only to the extent that perturbation of feature inputs is feasible in the real world. We formulate the problem of feasibility as preserving causal relationships among input features and present a method that uses (partial) structural causal models to generate actionable counterfactuals. When feasibility constraints may not be easily expressed, we propose an alternative method that optimizes for feasibility as people interact with its output and provide oracle-like feedback. Our experiments on a Bayesian network and the widely used "Adult" dataset show that our proposed methods can generate counterfactual explanations that satisfy feasibility constraints.

The Information Commissioner's Office (ICO) is putting forward a regulation that businesses and other organizations are required to explain decisions made by artificial intelligence (AI) or face multimillion-dollar fines if unable to. The guidance will provide advice such as how to explain the procedures, services, and outcomes delivered or assisted by AI to affected individuals. The report would detail the documentation of the decision-making process and data used to arrive at a decision. In extreme cases, organizations that fail to comply may face a fine of up to 4 percent of a company's global turnover, under the EU's data protection law. The new guidance is crucial as many firms in the UK are using some form of AI to execute critical business decisions, such as shortlisting and hiring candidates for roles. At the same time, two-thirds of UK financial services rely on AI to support customer services, drive business decisions and transactions.

We study the interpretability of predictive systems that use high-dimensonal behavioral and textual data. Examples include predicting product interest based on online browsing data and detecting spam emails or objectionable web content. Recently, counterfactual explanations have been proposed for generating insight into model predictions, which focus on what is relevant to a particular instance. Conducting a complete search to compute counterfactuals is very time-consuming because of the huge dimensionality. To our knowledge, for behavioral and text data, only one model-agnostic heuristic algorithm (SEDC) for finding counterfactual explanations has been proposed in the literature. However, there may be better algorithms for finding counterfactuals quickly. This study aligns the recently proposed Linear Interpretable Model-agnostic Explainer (LIME) and Shapley Additive Explanations (SHAP) with the notion of counterfactual explanations, and empirically benchmarks their effectiveness and efficiency against SEDC using a collection of 13 data sets. Results show that LIME-Counterfactual (LIME-C) and SHAP-Counterfactual (SHAP-C) have low and stable computation times, but mostly, they are less efficient than SEDC. However, for certain instances on certain data sets, SEDC's run time is comparably large. With regard to effectiveness, LIME-C and SHAP-C find reasonable, if not always optimal, counterfactual explanations. SHAP-C, however, seems to have difficulties with highly unbalanced data. Because of its good overall performance, LIME-C seems to be a favorable alternative to SEDC, which failed for some nonlinear models to find counterfactuals because of the particular heuristic search algorithm it uses. A main upshot of this paper is that there is a good deal of room for further research. For example, we propose algorithmic adjustments that are direct upshots of the paper's findings.

We developed an explainable artificial intelligence (AI) early warning score (xAI-EWS) system for early detection of acute critical illness. While maintaining a high predictive performance, our system explains to the clinician on which relevant electronic health records (EHRs) data the prediction is grounded. Acute critical illness is often preceded by deterioration of routinely measured clinical parameters, e.g., blood pressure and heart rate. Early clinical prediction is typically based on manually calculated screening metrics that simply weigh these parameters, such as Early Warning Scores (EWS). The predictive performance of EWSs yields a tradeoff between sensitivity and specificity that can lead to negative outcomes for the patient. Previous work on EHR-trained AI systems offers promising results with high levels of predictive performance in relation to the early, real-time prediction of acute critical illness. However, without insight into the complex decisions by such system, clinical translation is hindered. In this letter, we present our xAI-EWS system, which potentiates clinical translation by accompanying a prediction with information on the EHR data explaining it.

Explainable AI or shortly XAI is a domain that deals with maintaining transparency to the decision making capability of complex machine learning models and algorithms. In this article, we will take a look at such a tool that is built for the purpose of making AI explainable. A simple way to understand this concept is to compare the decision-making process of humans with that of the machines. How do we humans come to a decision? We often make decisions whether they are small insignificant decisions like what outfit to wear for an event, to highly complex decisions that involve risks such as investments or loan approvals.

In computational models of argumentation, the justification of statements has drawn less attention than the construction and justification of arguments. As a consequence, significant losses of sensitivity and expressiveness in the treatment of statement statuses can be incurred by otherwise appealing formalisms. In order to reappraise statement statuses and, more generally, to support a uniform modelling of different phases of the argumentation process we introduce multi-labelling systems, a generic formalism devoted to represent reasoning processes consisting of a sequence of labelling stages. In this context, two families of multi-labelling systems, called argument-focused and statement-focused approach, are identified and compared. Then they are shown to be able to encompass several prominent literature proposals as special cases, thereby enabling a systematic comparison evidencing their merits and limits. Further, we show that the proposed model supports tunability of statement justification by specifying a few alternative statement justification labellings, and we illustrate how they can be seamlessly integrated into different formalisms.

Artificial intelligence is set to transform global productivity, working patterns, and lifestyles and create enormous wealth. Research firm Gartner expects the global AI economy to increase from about $1.2 trillion last year to about $3.9 Trillion by 2022, while McKinsey sees it delivering global economic activity of around $13 trillion by 2030. AI techniques, especially Deep Learning (DL) models are revolutionizing the business and technology world with jaw-dropping performances in one application area after another -- image classification, object detection, object tracking, pose recognition, video analytics, synthetic picture generation -- just to name a few. They are being used in -- healthcare, I.T. services, finance, manufacturing, autonomous driving, video game playing, scientific discovery, and even the criminal justice system. However, they are like anything but classical Machine Learning (ML) algorithms/techniques.

Counterfactual explanations help users understand why machine learned models make certain decisions, and more specifically, how these decisions can be changed. In this work, we frame the problem of finding counterfactual explanations -- the minimal perturbation to an input such that the prediction changes -- as an optimization task. Previously, optimization techniques for generating counterfactual examples could only be applied to differentiable models, or alternatively via query access to the model by estimating gradients from randomly sampled perturbations. In order to accommodate non-differentiable models such as tree ensembles, we propose using probabilistic model approximations in the optimization framework. We introduce a novel approximation technique that is effective for finding counterfactual explanations while also closely approximating the original model. Our results show that our method is able to produce counterfactual examples that are closer to the original instance in terms of Euclidean, Cosine, and Manhattan distance compared to other methods specifically designed for tree ensembles.

Artificial intelligence is set to transform global productivity, working patterns, and lifestyles and create enormous wealth.