EHHN: An Event-driven Heterogeneous Hypergraph Network for Object-Centric Next Activity Prediction
arXiv:2607.01785v1 Announce Type: new Abstract: Next activity prediction helps service-oriented processes anticipate upcoming steps before delays, exceptions, or service-level risks occur. Most existing methods assume classical single-case event logs, whereas real service processes often involve events shared by multiple typed business objects. Object-centric event logs (OCELs) capture such interactions, but current predictors remain limited. Flattening-based approaches lose cross-object context, and native OCEL graph-based approaches encode multi-object events through pairwise relations. Exis
The proliferation of complex, interlinked business processes necessitates more sophisticated prediction models beyond single-case event logs.
Improved next activity prediction in object-centric processes can significantly reduce operational delays, manage exceptions, and mitigate service-level risks across various industries.
The ability to accurately anticipate steps in multi-object, event-driven processes using heterogeneous hypergraph networks represents a leap beyond traditional single-case or pairwise-relation methods.
- · Service-oriented businesses
- · Process mining software providers
- · Logistics and supply chain management
- · AI/ML researchers
- · Businesses relying on reactive process management
- · Legacy process prediction systems
Increased efficiency and reduced costs in complex operational workflows.
New standards and best practices for managing and analyzing object-centric event logs will emerge.
Enhanced automation layers built on these predictive capabilities could allow for fully autonomous process management in certain domains.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG