---
title: "Survey and Cross-benchmark Comparison of Remaining Time Prediction Methods in Business Process Monitoring"
type: source
tags: [ppm, survey, benchmark, remaining-time, hub]
authors: [Verenich Ilya; Dumas Marlon; La Rosa Marcello; Maggi Fabrizio Maria; Teinemaa Irene]
year: 2019
venue: "ACM Transactions on Intelligent Systems and Technology (TIST), July 2019"
kind: paper
raw_path: "raw/Predictive process monitoring/Verenich 2018.pdf"
duplicate_of_raw: "raw/Predictive process monitoring/Verenich2019.pdf"
created: 2026-04-13
updated: 2026-04-13
key_claims:
  - Systematic literature review of remaining-time prediction methods (focused scope; complements the outcome-PPM benchmark).
  - Taxonomy of time-related prediction methods capturing specificities of remaining-time prediction.
  - Cross-benchmark of 16 representative methods on 16 real-life logs from diverse industry domains.
  - Provides practitioner recommendations on method selection by scenario.
---

# Verenich et al. 2019 — Survey & Cross-Benchmark of Remaining-Time PPM

**Hub survey/benchmark** for [[concepts/remaining-time-prediction|remaining-time prediction]]. Complements Teinemaa et al.'s outcome-PPM benchmark ([[sources/2016-teinemaa-outcome-ppm-review]]) with a focused time-related-prediction taxonomy and empirical evaluation.

## Contribution
1. **Systematic literature review** ([[methods/systematic-literature-review|SLR]]) of remaining-time methods (scope: time, cycle time, remaining time, duration).
2. **Taxonomy** distinguishing time-specific method classes.
3. **Cross-benchmark** — 16 methods on 16 logs from different industries.
4. **Practitioner guidance** on method selection.

## Significance
Together with [[sources/2016-teinemaa-outcome-ppm-review]] (outcome benchmark) and [[sources/2020-rama-maneiro-deep-learning-ppm-review]] (deep-learning benchmark), anchors the **PPM survey triad** — required reading for anyone entering the field.

## Note on duplicates in `raw/`
`Verenich 2018.pdf` is the arXiv preprint (2018); `Verenich2019.pdf` is the published ACM TIST version (2019). Different MD5; same paper.

## Cited by
- [[sources/2023-riess-temporal-loss-remaining-cycle-time]] — Riess cites Verenich et al. as the canonical cross-benchmark baseline when introducing temporally weighted losses and Temporal Consistency.
- [[sources/2024-riess-synbps-simulation-framework]] — cited for the canonical PPM benchmark setup motivating controlled synthetic evaluation.

## Connections
**Concepts:** [[concepts/predictive-process-monitoring]] · [[concepts/remaining-time-prediction]] · [[concepts/trace-encoding]]
**Authors:** [[entities/ilya-verenich]] · [[entities/marlon-dumas]] · [[entities/marcello-la-rosa]] · [[entities/fabrizio-maggi]] · [[entities/irene-teinemaa]]