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

arXiv cs.AI / 3/31/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper argues that conventional predictive process monitoring methods are sub-symbolic and may not enforce domain rules needed for compliance.
It proposes a neuro-symbolic framework that uses Logic Tensor Networks (LTNs) to inject explicit process constraints (rules/logic) into the prediction model.
The approach is implemented as a four-stage pipeline: feature extraction, rule extraction, knowledge base creation, and knowledge injection.
Experiments indicate the method improves both compliance adherence and prediction accuracy versus baseline models across compliance-aware settings.

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.