Knowledge-Driven Modulation of Neural Networks with Attention Mechanism for Next Activity Prediction

TL;DR

This paper introduces a neural network system with attention mechanisms that incorporates background process knowledge to improve next activity prediction in predictive process monitoring, especially during exceptional cases or concept drift.

Contribution

It presents a novel Symbolic[Neuro] system that leverages procedural process models to enhance neural network predictions in process monitoring tasks.

Findings

Improved prediction accuracy on real-life logs.

Effective handling of exceptional process executions.

Enhanced robustness during concept drift.

Abstract

Predictive Process Monitoring (PPM) aims at leveraging historic process execution data to predict how ongoing executions will continue up to their completion. In recent years, PPM techniques for the prediction of the next activities have matured significantly, mainly thanks to the use of Neural Networks (NNs) as a predictor. While their performance is difficult to beat in the general case, there are specific situations where background process knowledge can be helpful. Such knowledge can be leveraged for improving the quality of predictions for exceptional process executions or when the process changes due to a concept drift. In this paper, we present a Symbolic[Neuro] system that leverages background knowledge expressed in terms of a procedural process model to offset the under-sampling in the training data. More specifically, we make predictions using NNs with attention mechanism, an emerging technology in the NN field. The system has been tested on several real-life logs showing an improvement in the performance of the prediction task.