Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models
It addresses the problem of improving explainability for practitioners in predictive process monitoring, though it is incremental by focusing on evaluation and guidelines rather than new methods.
The paper tackles the lack of actionable explainability in process outcome prediction by defining interpretability and faithfulness, and it benchmarks seven classifiers on thirteen real-life event logs to provide guidelines for model selection.
Although a recent shift has been made in the field of predictive process monitoring to use models from the explainable artificial intelligence field, the evaluation still occurs mainly through performance-based metrics, thus not accounting for the actionability and implications of the explanations. In this paper, we define explainability through the interpretability of the explanations and the faithfulness of the explainability model in the field of process outcome prediction. The introduced properties are analysed along the event, case, and control flow perspective which are typical for a process-based analysis. This allows comparing inherently created explanations with post-hoc explanations. We benchmark seven classifiers on thirteen real-life events logs, and these cover a range of transparent and non-transparent machine learning and deep learning models, further complemented with explainability techniques. Next, this paper contributes a set of guidelines named X-MOP which allows selecting the appropriate model based on the event log specifications, by providing insight into how the varying preprocessing, model complexity and explainability techniques typical in process outcome prediction influence the explainability of the model.