Contextual events improve prediction of next process steps
Leveraging contextual events on structure-aware next activity prediction
Machine LearningArtificial Intelligence
Summary
Predicting the next step in a process can help businesses plan and react better. But often, existing methods don’t fully use the context around the process, like conditions or other related events. The authors introduce a new way to encode these contexts using graphs that represent process instances and feed them to a neural network. Their tests with real-world data show that including this contextual information helps make better predictions about what will happen next in ongoing processes.
What this means in practice
- •For business process analysts: Improve forecasting of the next steps in operational workflows by factoring environmental conditions represented in event data.
- •For it operations teams: Enhance automated monitoring tools to detect upcoming process events using context-aware graph models for better system reliability.
Authors
Alessandro Mele, Claudia Diamantini, Domenico Potena
Abstract
Predictive process monitoring aims at forecasting various aspects of running processes. Among the different tasks, next activity prediction represents the most extensively investigated. However, only a limited number of existing approaches explicitly encode contextual information, i.e., the environmental conditions in which the process is executed, typically modeled through event log attributes or aggregated measures. In this paper, an approach based on the concept of Instance Graphs is introduced. To incorporate contextual process instances, several encoding strategies are proposed and evaluated by measuring their impact on prediction performance. For each encoding strategy, a set of prefix-Instance Graphs is generated and subsequently provided as input to a Graph Neural Network for the classification task. The proposed approach is evaluated on multiple real-world event logs, and the experimental results demonstrate that incorporating contextual process instances benefits prediction performance.