What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rules
Abstract
In real-world applications, being able to explain why a prediction is made is often as important - if not more so - than achieving high accuracy. However, existing methods for sequential event prediction typically prioritize accuracy at the expense of interpretability. Neuro-symbolic approaches offer a promising direction to improve interpretability by learning symbolic rules, but extending them to next-event prediction is challenging due to the presence of temporal dependencies. We introduce RULES, a neuro-symbolic model that learns sequential rules directly from data, and combine it with a residual network to form RUNES (Rule Network for Event Sequences). RULES accurately recovers ground truth rules from synthetic data and discovers compact, interpretable rule sets on real data. RUNES combines these rules additively with a residual network, achieving competitive accuracy while providing transparent access to active rules and how residuals adjust predictions.
Related
- Equation discovery for climate impact: emulating impact models for unexplored climate scenario with interpretable symbolic regression
- BRP-GABLE: An Interpretable Rule-Based Prediction Framework for Multiple Outcome Types
- Fragment-Level Graph Encoding for Interpretable Molecular Property Prediction
- Interpretable Social Network Churn Prediction via Ergodic Markov Chains
- Sequential Certification of Threshold Decisions in Rare-Event Risk Prediction
BibTeX
@misc{bauerschmidt2026what,
title = {{What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rules}},
author = {Tim Nico Bauerschmidt and Isabel Valera and Jilles Vreeken},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.31114},
eprint = {2610.31114},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.31114},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rules
AU - Tim Nico Bauerschmidt
AU - Isabel Valera
AU - Jilles Vreeken
PY - 2026
DA - 2026/10/22
PB - arXiv
DO - 10.48550/arxiv.2610.31114
UR - https://arxiv.org/abs/2610.31114
AB - In real-world applications, being able to explain why a prediction is made is often as important - if not more so - than achieving high accuracy. However, existing methods for sequential event prediction typically prioritize accuracy at the expense of interpretability. Neuro-symbolic approaches offer a promising direction to improve interpretability by learning symbolic rules, but extending them to next-event prediction is challenging due to the presence of temporal dependencies. We introduce RULES, a neuro-symbolic model that learns sequential rules directly from data, and combine it with a residual network to form RUNES (Rule Network for Event Sequences). RULES accurately recovers ground truth rules from synthetic data and discovers compact, interpretable rule sets on real data. RUNES combines these rules additively with a residual network, achieving competitive accuracy while providing transparent access to active rules and how residuals adjust predictions.
ER -