Explaining the root causes of unit-level changes
Existing methods of explainable AI and interpretable ML cannot explain change in the values of an output variable for a statistical unit in terms of the change in the input values and the change in the "mechanism" (the function transforming input to output). We propose two methods based on counterfactuals for explaining unit-level changes at various input granularities using the concept of Shapley values from game theory. These methods satisfy two key axioms desirable for any unit-level change attribution method. Through simulations, we study the reliability and the scalability of the proposed methods. We get sensible results from a case study on identifying the drivers of the change in the earnings for individuals in the US.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Explaining Concept Drift through the Evolution of Group Counterfactuals
Machine learning models in dynamic environments often suffer from concept drift, where changes in the data distribution degrade performance. While detecting this drift is a well-studied topic, explaining how and why the …
A Framework for Explainable Concept Drift Detection in Process Mining
Rapidly changing business environments expose companies to high levels of uncertainty. This uncertainty manifests itself in significant changes that tend to occur over the lifetime of a process and possibly affect its pe…
Drift DetectionAutomating Detection and Root-Cause Analysis of Flaky Tests in Quantum Software
Like classical software, quantum software systems rely on automated testing. However, their inherently probabilistic outputs make them susceptible to quantum flakiness -- tests that pass or fail inconsistently without co…
Identifying Patient-Specific Root Causes of Disease
Complex diseases are caused by a multitude of factors that may differ between patients. As a result, hypothesis tests comparing all patients to all healthy controls can detect many significant variables with inconsequent…
Causal InferenceDiagnosticAutomatic Cause Detection of Performance Problems in Web Applications
The execution of similar units can be compared by their internal behaviors to determine the causes of their potential performance issues. For instance, by examining the internal behaviors of different fast or slow web re…
Clustering