The WHY in Business Processes: Discovery of Causal Execution Dependencies
Fabiana Fournier, Lior Limonad, Inna Skarbovsky, Yuval David
TL;DR
The paper addresses the gap between associative process discovery and true causal understanding in business processes by introducing a Causal BP (CBP) view derived from activity timing using LiNGAM. It presents a method that overlays CBP onto conventional PD outputs, highlighting discrepancies across three causal patterns: confounder, mediator, and collider, to enable robust intervention reasoning. The approach is demonstrated on synthetic data and real benchmarks (Sepsis and Request-for-Payment), showing that PD alone can misrepresent causal dependencies, while the CBP overlay provides actionable insights for process improvement and explainability. The method is designed to be algorithm-agnostic and scalable, offering a practical pathway to integrate causal reasoning into existing process mining tooling and decision support workflows.
Abstract
Unraveling the causal relationships among the execution of process activities is a crucial element in predicting the consequences of process interventions and making informed decisions regarding process improvements. Process discovery algorithms exploit time precedence as their main source of model derivation. Hence, a causal view can supplement process discovery, being a new perspective in which relations reflect genuine cause-effect dependencies among the tasks. This calls for faithful new techniques to discover the causal execution dependencies among the tasks in the process. To this end, our work offers a systematic approach to the unveiling of the causal business process by leveraging an existing causal discovery algorithm over activity timing. In addition, this work delves into a set of conditions under which process mining discovery algorithms generate a model that is incongruent with the causal business process model, and shows how the latter model can be methodologically employed for a sound analysis of the process. Our methodology searches for such discrepancies between the two models in the context of three causal patterns, and derives a new view in which these inconsistencies are annotated over the mined process model. We demonstrate our methodology employing two open process mining algorithms, the IBM Process Mining tool, and the LiNGAM causal discovery technique. We apply it to a synthesized dataset and two open benchmark datasets.