Time-Aware and Transition-Semantic Graph Neural Networks for Interpretable Predictive Business Process Monitoring

TL;DR

This paper introduces a novel, interpretable graph neural network framework for predictive business process monitoring that incorporates temporal decay and transition semantics, improving accuracy and explainability.

Contribution

It proposes a unified GNN model with time decay attention and transition semantics embedding, advancing interpretability and performance in process prediction tasks.

Findings

Achieves competitive accuracy on five benchmarks.

Demonstrates the effectiveness of temporal decay attention.

Provides multilevel interpretability visualizations.

Abstract

Predictive Business Process Monitoring (PBPM) aims to forecast future events in ongoing cases based on historical event logs. While Graph Neural Networks (GNNs) are well suited to capture structural dependencies in process data, existing GNN-based PBPM models remain underdeveloped. Most rely either on short prefix subgraphs or global architectures that overlook temporal relevance and transition semantics. We propose a unified, interpretable GNN framework that advances the state of the art along three key axes. First, we compare prefix-based Graph Convolutional Networks(GCNs) and full trace Graph Attention Networks(GATs) to quantify the performance gap between localized and global modeling. Second, we introduce a novel time decay attention mechanism that constructs dynamic, prediction-centered windows, emphasizing temporally relevant history and suppressing noise. Third, we embed transition type semantics into edge features to enable fine grained reasoning over structurally ambiguous traces. Our architecture includes multilevel interpretability modules, offering diverse visualizations of attention behavior. Evaluated on five benchmarks, the proposed models achieve competitive Top-k accuracy and DL scores without per-dataset tuning. By addressing architectural, temporal, and semantic gaps, this work presents a robust, generalizable, and explainable solution for next event prediction in PBPM.