---
title: Remaining Time Prediction
type: concept
tags: [ppm, prediction, regression, time, earliness, temporal-consistency]
sources:
  - "[[sources/2017-tax-lstm-process-prediction]]"
  - "[[sources/2017-navarin-lstm-data-aware-remaining-time]]"
  - "[[sources/2019-verenich-survey-ppm]]"
  - "[[sources/2023-riess-temporal-loss-remaining-cycle-time]]"
  - "[[sources/2026-padella-llm-features-ppm]]"
created: 2026-04-13
updated: 2026-05-11
---

# Remaining Time Prediction

A [[concepts/predictive-process-monitoring|PPM]] task: given a prefix of an event trace, predict the **remaining execution time** until the case completes.

## Formulation
- **Input:** prefix `⟨e₁, …, eₖ⟩` with timestamps.
- **Output:** scalar `t_remaining` (regression).
- **Training data:** for each prefix extracted from a completed case, label = (case completion timestamp − prefix-end timestamp).

## Canonical approaches
- **Transition system annotation** — van der Aalst et al.; annotate states of a transition system with mean remaining time.
- **Regression trees / ensembles** — feature-engineered. Includes the CatBoost regressor used as a benchmark in [[sources/2026-padella-llm-features-ppm|Padella et al. 2026]].
- **[[concepts/lstm-ppm|LSTM]] regression head** — often in multi-task setup with next-activity prediction.
- **[[concepts/transformer-ppm|Transformer]] regressors** — recent state of the art (e.g. PGTNet — Process Graph Transformer Network — used as benchmark in Padella et al. 2026).
- **[[concepts/llm-based-ppm|LLM-based prediction]]** — emerging family, particularly competitive in data-scarce settings. [[sources/2026-padella-llm-features-ppm|Padella, de Leoni & Dumas 2026]] document Gemini 2.5 Flash Thinking trained on 100 traces matching or surpassing CatBoost / PGTNet on the full BPI12 / Bac / Hospital event logs for Total Time MAE.

## Evaluation — three axes
- **Accuracy** — MAE / MAPE / RMSE in time units (hours, days).
- **Earliness** — accuracy at early prefixes, when information is minimal and prediction is hardest ([[sources/2019-verenich-survey-ppm|Verenich et al. 2019]]; [[sources/2023-riess-temporal-loss-remaining-cycle-time|Riess 2023]]). Operationally critical for queue prioritisation and dynamic resource planning.
- **Temporal Consistency (TC)** — the degree to which consecutive predictions follow the natural monotonic decrease of true remaining time ([[sources/2023-riess-temporal-loss-remaining-cycle-time|Riess 2023]]). Proposed axis; none of the standard losses evaluated (unweighted MAE, exponential / power / moderate temporal decay) produce strictly monotonically decreasing predictions.
- **Error curves over prefix length** — accuracy typically improves as more of the case has been observed.

### Loss-function design
Standard: unweighted **L1 (MAE)** — robust to time-between-event outliers and typically outperforms MSE ([[sources/2019-verenich-survey-ppm|Verenich et al. 2019]]).
**Temporally weighted L1** ([[sources/2023-riess-temporal-loss-remaining-cycle-time|Riess 2023]]): three variants — exponential decay (MAEEtD), power decay (MAEPtD), moderate decay (MAEMtD) — upweight early-prefix residuals. Exponential decay gave statistically significant earliness improvements on 2 of 4 public event logs; should be treated as a tunable hyper-parameter, with a potential trade-off against temporal consistency.

## Challenges
- **Long-tail case durations** — outlier long cases skew error metrics.
- **Case heterogeneity** — different variants have very different remaining-time distributions.
- **Non-stationarity** — process behaviour drifts; models need retraining ([[concepts/concept-drift]]).
- **Data-awareness matters** — incorporating case data (attributes, resources) outperforms control-flow-only ([[sources/2017-navarin-lstm-data-aware-remaining-time]] and others).
- **Small-benchmark external validity** — most published methods evaluated on 3–9 public event logs; controlled synthetic evaluation via [[concepts/business-process-simulation|parametric simulation]] ([[sources/2024-riess-synbps-simulation-framework|SynBPS]]) recommended for data-generating-process-factor analysis.

## Related
[[concepts/predictive-process-monitoring]] · [[concepts/next-activity-prediction]] · [[concepts/outcome-prediction]] · [[concepts/trace-encoding]] · [[concepts/concept-drift]] · [[concepts/business-process-simulation]] · [[concepts/llm-based-ppm]]