Compliance-Aware Predictive Process Monitoring: A Neuro-Symbolic Approach

Abstract

Existing approaches for predictive process monitoring are sub-symbolic, meaning that they learn correlations between descriptive features and a target feature fully based on data, e.g., predicting the surgical needs of a patient based on historical events and biometrics. However, such approaches fail to incorporate domain-specific process constraints (knowledge), e.g., surgery can only be planned if the patient was released more than a week ago, limiting the adherence to compliance and providing less accurate predictions. In this paper, we present a neuro-symbolic approach for predictive process monitoring, leveraging Logic Tensor Networks (LTNs) to inject process knowledge into predictive models. The proposed approach follows a structured pipeline consisting of four key stages: 1) feature extraction; 2) rule extraction; 3) knowledge base creation; and 4) knowledge injection. Our evaluation shows that, in addition to learning the process constraints, the neuro-symbolic model also achieves better performance, demonstrating higher compliance and improved accuracy compared to baseline approaches across all compliance-aware experiments.

Figures (5)

• Figure 1: Binary classification backbone implemented as an LTN computational graph bagase_2022.
• Figure 2: The pipeline followed in the approach, which consists of feature extraction, rule extraction, knowledge base creation and injection, and then the creation of the neuro-symbolic model leveraging the LTN framework.
• Figure 3: The three ways of injecting knowledge: (A) feature expansion for class-dependent, non-outcome-oriented knowledge, (B) output refinement for class-dependent, outcome-oriented knowledge, and (C) parallel constraints for class-independent knowledge. Each injection pathway addresses a different failure mode of purely data-driven predictors: feature expansion propagates declarative facts such as "elderly diabetic patients require special monitoring" into the feature space, output refinement operationalizes outcome rules like "timely antibiotics lower complication risk" directly on the predicate outputs, and parallel constraints regularize the shared representation by penalizing process executions structural rules such as "medical history review must precede physical examination."
• Figure 4: Ablation study for LTN-T of the different injection methods with 5 different seeds. Injection techniques were first evaluated individually (i.e., feature expansion LTN_A and output refinement LTN_B), followed by an evaluation of their possible combinations, where the LTN_ABC is the main configuration. The letters used to denote the configurations correspond to the injection methods in \ref{['fig:approach']}.
• Figure 5: Compliance scores obtained with 5 different seeds comparing purely data-driven baselines with knowledge-enhanced variants.