# Decision-Aware Suffix Prediction and Reasoning of Business Processes

arXiv: https://arxiv.org/abs/2609.06169 · HTML: https://mlsanity.com/paper/2609.06169/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 5 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [A Semantic Loss Function for Deep Learning with Symbolic Knowledge](https://mlsanity.com/paper/1711.11157/) (2017)
- [Predicting Process Behaviour using Deep Learning](https://mlsanity.com/paper/1612.04600/) (2016)
- [A Deep Adversarial Model for Suffix and Remaining Time Prediction of Event Sequences](https://mlsanity.com/paper/2102.07298/) (2021)
- [Neuro-Symbolic Predictive Process Monitoring](https://mlsanity.com/paper/2509.00834/) (2025)
- [Explainable Predictive Decision Mining for Operational Support](https://mlsanity.com/paper/2210.16786/) (2022)
- [Masking Neural Networks Using Reachability Graphs to Predict Process Events](https://mlsanity.com/paper/2108.00404/) (2021)
- [Compliance-Aware Predictive Process Monitoring: A Neuro-Symbolic Approach](https://mlsanity.com/paper/2603.26948/) (2026)

## Abstract (arXiv)

Suffix prediction forecasts the remaining sequence of events of a running case until completion. Most approaches rely on neural networks trained on event logs, which, on average, perform well but struggle with short prefixes or targets belonging to a rare process variant. In such scenarios, the correct path may cross multiple branching decisions, determined primarily by case- and event-level attributes, a signal that NN-based suffix prediction models tend to underweight because they may heavily weight (dense) event labels. Decision mining extracts rules for such decisions from the event log, but has so far been applied only to post-hoc and what-if analysis, not suffix prediction. We therefore extend suffix prediction with decision mining, introducing a decision-aware suffix prediction framework, a neuro-symbolic approach that enables reasoning about predicted events via mined decision rules. Experiments on three of four event logs and three suffix predictors show that the framework can improve suffix prediction, especially for short prefixes but also for rare process variants, and adds intrinsic interpretability.