# HOEG: A New Approach for Object-Centric Predictive Process Monitoring

arXiv: https://arxiv.org/abs/2404.05316 · HTML: https://mlsanity.com/paper/2404.05316/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 8 Apr 2024.

## Builds on (most cited first, 7 of 7)

- [Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks](https://mlsanity.com/paper/1810.02244/) (2018)
- [Design Space for Graph Neural Networks](https://mlsanity.com/paper/2011.08843/) (2020)
- [Discovering Object-Centric Petri Nets](https://mlsanity.com/paper/2010.02047/) (2020)
- [Defining Cases and Variants for Object-Centric Event Data](https://mlsanity.com/paper/2208.03235/) (2022)
- [Object-centric Process Predictive Analytics](https://mlsanity.com/paper/2203.02801/) (2022)
- [Predictive Object-Centric Process Monitoring](https://mlsanity.com/paper/2207.10017/) (2022)
- [A Framework for Extracting and Encoding Features from Object-Centric Event Data](https://mlsanity.com/paper/2209.01219/) (2022)

## Built on by (most cited first, 2 of 2)

- [Extending predictive process monitoring for collaborative processes](https://mlsanity.com/paper/2409.09212/) (2024)
- [EHHN: An Event-driven Heterogeneous Hypergraph Network for Object-Centric Next Activity Prediction](https://mlsanity.com/paper/2607.01785/) (2026)

## Abstract (arXiv)

Predictive Process Monitoring focuses on predicting future states of ongoing process executions, such as forecasting the remaining time. Recent developments in Object-Centric Process Mining have enriched event data with objects and their explicit relations between events. To leverage this enriched data, we propose the Heterogeneous Object Event Graph encoding (HOEG), which integrates events and objects into a graph structure with diverse node types. It does so without aggregating object features, thus creating a more nuanced and informative representation. We then adopt a heterogeneous Graph Neural Network architecture, which incorporates these diverse object features in prediction tasks. We evaluate the performance and scalability of HOEG in predicting remaining time, benchmarking it against two established graph-based encodings and two baseline models. Our evaluation uses three Object-Centric Event Logs (OCELs), including one from a real-life process at a major Dutch financial institution. The results indicate that HOEG competes well with existing models and surpasses them when OCELs contain informative object attributes and event-object interactions.