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

Fabrizio De Santis; Gyunam Park; Wil M. P. van der Aalst; Francesco Zanichelli

cs.AIMar 27, 2026

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

Authors: Fabrizio De Santis, Gyunam Park, Wil M. P. van der Aalst, Francesco Zanichelli

Organizations: University of Parma, Parma, Italy · Eindhoven University of Technology, Eindhoven, Netherlands · RWTH Aachen University, Aachen, Germany

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 & tables

Figure 1: Binary classification backbone implemented as an LTN computational graph [ 2 ] .

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.”

Model	Sepsis		BPIC2012		BPIC2017		Traffic fines
Model	Accuracy	F1	Accuracy	F1	Accuracy	F1	Accuracy	F1
LSTM	81,86 ± 1,57	71.61 ± 4.70	53.19 ± 2.45	52.49 ± 1.99	64.62 ± 0.76	64.04 ± 1.15	77.34 ± 1.54	77.27 ± 1.65
TRF	81,53 ± 2,31	73.66 ± 2.78	58.80 ± 1.21	56.15 ± 1.09	69.22 ± 3.11	68.93 ± 3.53	78.26 ± 1.51	78.23 ± 1.52
LSTM-FE	81,71 ± 1.60	70.49 ± 3.87	51.89 ± 0.97	51.80 ± 1.03	63.35 ± 0.54	62.20 ± 0.49	77.15 ± 0.61	77.05 ± 0.69
TRF-FE	78.61 ± 3.34	67.01 ± 4.09	62.29 ± 2.49	58.83 ± 2.16	66.41 ± 1.64	65.77 ± 1.97	75.18 ± 0.81	74.90 ± 0.92
LSTM-SL	79.90 ± 2.72	69.70 ± 4.59	53.70 ± 1.94	53.08 ± 1.52	64.98 ± 0.59	64.34 ± 0.63	77.54 ± 1.42	77.46 ± 1.52

Table 1: Performance on compliance-aware test set comparing purely data-driven baselines (LSTM, TFR, LTSM-FE, TFR-FE) with knowledge-enhanced variants. Results show mean and standard deviation over 5 seeds.

Panel of Figure 4 — 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 Fig. 3 .

Panel of Figure 5 — Figure 5: Compliance scores obtained with 5 different seeds comparing purely data-driven baselines with knowledge-enhanced variants.

Explore similar work

Neuro-Symbolic Learning for Predictive Process Monitoring via Two-Stage Logic Tensor Networks with Rule Pruning
Mar 27, 2026Fabrizio De Santis, Gyunam Park, Francesco ZanichelliPredictive Process Monitoring Neurosymbolic Learning
University of Parma, Parma, Italy · Eindhoven University of Technology, Eindhoven, Netherlands
Neuro-Symbolic Process Anomaly Detection
Mar 27, 2026Devashish Gaikwad, Wil M. P. van der Aalst, Gyunam ParkAnomaly Detection Process Mining
RWTH Aachen University, Aachen, Germany · Eindhoven University of Technology, Eindhoven, The Netherlands
Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda
Jun 11, 2026Alexander Rombach, Chantale Lauer, Nijat MehdiyevAI Assurance Business Process Automation
German Research Center for Artificial Intelligence (DFKI), Campus D3 2, 66123 Saarbrücken, Germany · Saarland University, Campus D3 2, 66123 Saarbrücken, Germany

Mar 27, 2026J/K move · Enter open · S save

Neuro-Symbolic Learning for Predictive Process Monitoring via Two-Stage Logic Tensor Networks with Rule Pruning

Fabrizio De Santis, Gyunam Park, Francesco Zanichelli

University of Parma, Parma, Italy · Eindhoven University of Technology, Eindhoven, Netherlands

Predictive Process Monitoring Neurosymbolic Learning Tensor Networks

Open paper AskPDF arXiv

Predictive modeling on sequential event data is critical for fraud detection and healthcare monitoring. Existing data-driven approaches learn correlations from historical data but fail to incorporate domain-specific sequential constraints and logical rules governing event relationships, limiting accuracy and regulatory compliance. For example, healthcare procedures must follow specific sequences, and financial transactions must adhere to compliance rules. We present a neuro-symbolic approach integrating domain knowledge as differentiable logical constraints using Logic Networks (LTNs). We formalize control-flow, temporal, and payload knowledge using Linear Temporal Logic and first-order logic. Our key contribution is a two-stage optimization strategy addressing LTNs' tendency to satisfy logical formulas at the expense of predictive accuracy. The approach uses weighted axiom loss during pretraining to prioritize data learning, followed by rule pruning that retains only consistent, contributive axioms based on satisfaction dynamics. Evaluation on four real-world event logs shows that domain knowledge injection significantly improves predictive performance, with the two-stage optimization proving essential knowledge (without it, knowledge can severely degrade performance). The approach excels particularly in compliance-constrained scenarios with limited compliant training examples, achieving superior performance compared to purely data-driven baselines while ensuring adherence to domain constraints.

Abstract

Explore similar work

Neuro-Symbolic Learning for Predictive Process Monitoring via Two-Stage Logic Tensor Networks with Rule Pruning

Neuro-Symbolic Process Anomaly Detection

Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda