Explainability of Predictive Process Monitoring Results: Can You See My Data Issues?

TL;DR

This paper investigates how different settings in predictive process monitoring affect explanations generated by XAI, revealing data issues and inconsistencies that impact user trust in ML-based predictions.

Contribution

It introduces a framework to analyze the influence of PPM settings on explanations and highlights the importance of data quality and configuration in generating trustworthy explanations.

Findings

Identified data inconsistencies affecting explanations

Demonstrated the impact of PPM settings on explanation quality

Highlighted the need for careful data and model configuration

Abstract

Predictive business process monitoring (PPM) has been around for several years as a use case of process mining. PPM enables foreseeing the future of a business process through predicting relevant information about how a running process instance might end, related performance indicators, and other predictable aspects. A big share of PPM approaches adopts a Machine Learning (ML) technique to address a prediction task, especially non-process-aware PPM approaches. Consequently, PPM inherits the challenges faced by ML approaches. One of these challenges concerns the need to gain user trust in the predictions generated. The field of explainable artificial intelligence (XAI) addresses this issue. However, the choices made, and the techniques employed in a PPM task, in addition to ML model characteristics, influence resulting explanations. A comparison of the influence of different settings on the generated explanations is missing. To address this gap, we investigate the effect of different PPM settings on resulting data fed into an ML model and consequently to a XAI method. We study how differences in resulting explanations may indicate several issues in underlying data. We construct a framework for our experiments including different settings at each stage of PPM with XAI integrated as a fundamental part. Our experiments reveal several inconsistencies, as well as agreements, between data characteristics (and hence expectations about these data), important data used by the ML model as a result of querying it, and explanations of predictions of the investigated ML model.