---
title: "A Deep Learning Approach for Predicting Process Behaviour at Runtime"
type: source
tags: [ppm, deep-learning, rnn, next-activity, foundational]
authors: [Evermann Joerg; Rehse Jana-Rebecca; Fettke Peter]
year: 2017
venue: "BPM 2016 Workshops, LNBIP 281, Springer: 327–338"
kind: paper
raw_path: "raw/Predictive process monitoring/A deep learning approach for predicting process behaviour at runtime evermann2017.pdf"
created: 2026-04-13
updated: 2026-04-13
key_claims:
  - First application of deep learning (RNN) to predictive process monitoring — specifically next-event prediction.
  - Event traces can be treated analogously to natural-language sentences; events are words.
  - Explicit process models are not needed — the RNN learns process logic implicitly.
  - Differences from NLP (smaller vocabulary, longer sequences, rule-driven structure) suggest RNNs may perform better on process prediction than on NLP.
---

# Evermann, Rehse, Fettke 2017 — Deep Learning for Process Behaviour at Runtime

The **first paper applying deep learning (specifically RNNs) to PPM**. Explicitly positioned as an exploratory contribution — demonstrating feasibility, not final performance.

## Contribution
- Frames next-event prediction as sequence modelling, borrowing the NLP analogy: *events are words, traces are sentences*.
- Uses RNNs (with embedding layer) instead of explicit process-model representations (HMMs, annotated transition systems).
- Notes three structural differences between process logs and NL: smaller vocab, potentially very long traces, rule-constrained sequences — all favourable to neural approaches.

## Significance
Serves as the baseline that **Tax et al. 2017** ([[sources/2017-tax-lstm-process-prediction]]) explicitly compares against and improves upon with LSTM and the broader multi-task setting. Together these two 2017 papers anchor the neural-PPM era.

## Connections
**Concepts:** [[concepts/predictive-process-monitoring]] · [[concepts/next-activity-prediction]] · [[concepts/lstm-ppm]]
**Authors:** [[entities/peter-fettke]] · [[entities/joerg-evermann]] · [[entities/jana-rebecca-rehse]]
**Related sources:** [[sources/2017-tax-lstm-process-prediction]]