Graph-based retrieval improves suffix prediction for process recommendations
Complete Suffix Prediction for Recommendation via Latent Retrieval over Process Graphs
Neural and Evolutionary Computing
Summary
Predicting what comes next after a series of steps is hard because the same beginning can lead to many different endings. The authors represent these sequences as graphs and use a special type of neural network to understand both the activities and the time between them. They train a model that matches beginnings to likely endings by learning to pull similar examples close in a shared space. Their method outperforms others in accuracy and timing on real-world datasets, showing graph-based methods can better recommend next steps in complex processes.
What this means in practice
- •For business process analysts: Predict possible future steps in workflows to improve decision-making in automated process monitoring.
- •For workflow automation developers: Enhance recommendation systems that suggest next actions based on partial process histories using graph-based retrieval.
Authors
Sarra Madad, Myriam Maumy, Fr{é}d{é}ric Bertrand, Yoann Valero
Abstract
Complete suffix prediction is challenging in sequential decision settings, where the same prefix can remain compatible with several plausible suffixes. We propose a graphbased metric-learning framework that reformulates complete suffix prediction as latent retrieval over process graphs. Prefixes and suffixes are represented as directed attributed graphs and encoded by edge-conditioned graph neural networks, allowing event-level activities and transition-level durations to be modelled jointly. Prefix representations are projected into the latent suffix space through a predictor trained with a joint reconstruction and contrastive objective strengthened using process-aware hard negatives. To stabilise the learned retrieval geometry, spectral normalisation, and retrieval robustness, spectral normalisation is applied to enforce a Lipschitz constraint on both encoders and predictor. Experiments on two real-life process datasets demonstrate that the proposed framework achieves the best overall results across nearly all evaluated criteria. It improves semantic suffix accuracy measured by normalized Damerau-Levenshtein distance, yields strong retrieval quality through Recall@1, Recall@5, and MRR@5, and maintains temporal plausibility according to Mean Absolute Error. These results show that graph-based latent retrieval is an effective alternative to sequential suffix prediction for recommendation-oriented process monitoring under structural and KPI-related constraints.