---
title: "Comparing and Combining Predictive Business Process Monitoring Techniques"
type: source
tags: [ppm, ensemble, constraint-based, ml, failure-prediction]
authors: [Metzger Andreas; Leitner Philipp; Ivanović Dragan; Schmieders Eric; Franklin Rod; Carro Manuel; Dustdar Schahram; Pohl Klaus]
year: 2015
venue: "IEEE Transactions on Systems, Man, and Cybernetics: Systems 45(2): 276–290"
kind: paper
raw_path: "raw/Predictive process monitoring/Comparing and Combining Predictive Business metzger2015.pdf"
created: 2026-04-13
updated: 2026-04-13
key_claims:
  - Predictive PPM techniques fall into three families - ML-based (data-driven), constraint-satisfaction (QoS aggregation), and combined.
  - Individual techniques and their combinations empirically compared on a real-life transportation-logistics case study (3942 instances).
  - Combining constraint-based with ML improves precision up to 14%, consistent with aggregation-then-learning intuitions.
---

# Metzger et al. 2015 — Comparing and Combining PPM Techniques

Early empirical survey / ensemble paper. Compares ML-based (classifier on running features), constraint-based (QoS aggregation over remaining sub-processes), and **combined** techniques on a real transport-logistics log.

## Contribution
- Categorisation of prior PPM families into ML vs constraint-satisfaction vs combined.
- Evaluation on 3942 process instances, five months of real data.
- Demonstrates **ensembling / combining** techniques outperforms either alone — an early instance of the "no single best model" thesis that [[sources/2017-tax-lstm-process-prediction|Tax et al. 2017]] later generalised with a unified LSTM.

## Significance
Represents the **pre-deep-learning PPM era** that neural methods would largely supersede from 2017 onward. Remains relevant where interpretability, small-data regimes, or constraint guarantees are required. Andreas Metzger ([[entities/andreas-metzger]]) continues to publish on related self-adaptive process monitoring — cited extensively in the APM Manifesto.

## Connections
**Concepts:** [[concepts/predictive-process-monitoring]] · [[concepts/outcome-prediction]]
**Authors:** [[entities/andreas-metzger]]