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

TL;DR

This paper introduces DiCE4EL, an extension of the DiCE counterfactual algorithm, tailored for process prediction explanations in event logs, incorporating milestone-awareness to improve interpretability of business process predictions.

Contribution

We develop DiCE4EL, a novel method that generates milestone-aware counterfactual explanations for process predictions, addressing limitations of existing algorithms in handling process domain knowledge and sequence data.

Findings

DiCE4EL effectively generates understandable counterfactual explanations for process predictions.

Incorporating milestone-awareness enhances interpretability of process prediction explanations.

The approach performs well on real-life event logs, demonstrating practical applicability.

Abstract

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 algorithms are opaque and a human decision-maker is unable to understand \emph{why} a certain activity was predicted. Recently, counterfactuals have been proposed in the literature to derive human-understandable explanations from predictive models. Current counterfactual approaches consist of finding the minimum feature change that can make a certain prediction flip its outcome. Although many algorithms have been proposed, their application to multi-dimensional sequence data like event logs has not been explored in the literature. In this paper, we explore the use of a recent, popular model-agnostic counterfactual algorithm, DiCE, in the context of predictive process analytics. The analysis reveals that DiCE is unable to derive explanations for process predictions, due to (1) process domain knowledge not being taken into account, (2) long traces of process execution that often tend to be less understandable, and (3) difficulties in optimising the counterfactual search with categorical variables. We design an extension of DiCE, namely DiCE4EL (DiCE for Event Logs), that can generate counterfactual explanations for process prediction, and propose an approach that supports deriving milestone-aware counterfactual explanations at key intermediate stages along process execution to promote interpretability. We apply our approach to a publicly available real-life event log and the analysis results demonstrate the effectiveness of the proposed approach.