We present a sensitivity analysis-based method for explaining prediction models that can be
applied to any type of classification or regression model. Its advantage over existing general …

Current research into algorithmic explanation methods for predictive models can be divided
into two main approaches: gradient-based approaches limited to neural networks and more …

We present a general method for explaining individual predictions of classification models.
The method is based on fundamental concepts from coalitional game theory and predictions …

A complexity of business dynamics often forces decision-makers to make decisions based
on subjective mental models, reflecting their experience. However, research has shown that …

We examine counterfactual explanations for explaining the decisions made by model-based
AI systems. The counterfactual approach we consider defines an explanation as a set of the …

Learning from data streams (incremental learning) is increasingly attracting research focus
due to many real-world streaming problems and due to many open challenges, among …

In this paper, we present a novel method for explaining the decisions of an arbitrary
classifier, independent of the type of classifier. The method works at the instance level …

Predictive machine learning models are increasingly being used at decisionmaking
institutions, such as central banks, governments, and international institutions (Doerr …

Feature construction can contribute to comprehensibility and performance of machine
learning models. Unfortunately, it usually requires exhaustive search in the attribute space …

We propose a method for explaining regression models and their predictions for individual
instances. The method successfully reveals how individual features influence the model and …