activity
20132025
most citedBenchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box

17 citations · 34 across the 15 of their papers we have counts for

collaborators
Showing 2021Show all

5 papers · 1 filter

cs.LG2021

Building Interpretable Models for Business Process Prediction using Shared and Specialised Attention Mechanisms

Bemali Wickramanayake, Zhipeng He, Chun Ouyang +3

In this paper, we address the "black-box" problem in predictive process analytics by building interpretable models that are capable to inform both what and why is a prediction. Pre…

cs.AI2021★ 3 cited

Explainable AI Enabled Inspection of Business Process Prediction Models

Chun Ouyang, Renuka Sindhgatta, Catarina Moreira

Modern data analytics underpinned by machine learning techniques has become a key enabler to the automation of data-led decision making. As an important branch of state-of-the-art…

cs.LG2021

DiCE4EL: Interpreting Process Predictions using a Milestone-Aware Counterfactual Approach

Chihcheng Hsieh, Catarina Moreira, Chun Ouyang

Predictive process analytics often apply machine learning to predict the future states of a running business~process. However, the internal mechanisms of many existing predictive a…

cs.AI2021

Order Effects in Bayesian Updates

Catarina Moreira, Jose Acacio de Barros

Order effects occur when judgments about a hypothesis's probability given a sequence of information do not equal the probability of the same hypothesis when the information is reve…

cs.AI2021

Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications

Yu-Liang Chou, Catarina Moreira, Peter Bruza +2

There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for…