PGTNet: A Process Graph Transformer Network for Remaining Time Prediction of Business Process Instances

TL;DR

PGTNet is a novel graph transformer model that predicts remaining time in business processes, outperforming existing methods especially for complex processes by capturing control-flow and long-range dependencies.

Contribution

The paper introduces PGTNet, a process graph transformer network that effectively models complex business processes for accurate remaining time prediction.

Findings

Outperforms state-of-the-art deep learning approaches on 20 real-world logs.

Most effective for highly complex processes with intricate control-flow.

Capable of considering multiple process perspectives during learning.

Abstract

We present PGTNet, an approach that transforms event logs into graph datasets and leverages graph-oriented data for training Process Graph Transformer Networks to predict the remaining time of business process instances. PGTNet consistently outperforms state-of-the-art deep learning approaches across a diverse range of 20 publicly available real-world event logs. Notably, our approach is most promising for highly complex processes, where existing deep learning approaches encounter difficulties stemming from their limited ability to learn control-flow relationships among process activities and capture long-range dependencies. PGTNet addresses these challenges, while also being able to consider multiple process perspectives during the learning process.