An Uncertainty-Aware ED-LSTM for Probabilistic Suffix Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mustroph, Henryk, Kunkler, Michel, Rinderle-Ma, Stefanie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916781676822528
author Mustroph, Henryk
Kunkler, Michel
Rinderle-Ma, Stefanie
author_facet Mustroph, Henryk
Kunkler, Michel
Rinderle-Ma, Stefanie
contents Suffix prediction of business processes forecasts the remaining sequence of events until process completion. Current approaches focus on predicting the most likely suffix, representing a single scenario. However, when the future course of a process is subject to uncertainty and high variability, the expressiveness of such a single scenario can be limited, since other possible scenarios, which together may have a higher overall probability, are overlooked. To address this limitation, we propose probabilistic suffix prediction, a novel approach that approximates a probability distribution of suffixes. The proposed approach is based on an Uncertainty-Aware Encoder-Decoder LSTM (U-ED-LSTM) and a Monte Carlo (MC) suffix sampling algorithm. We capture epistemic uncertainties via MC dropout and aleatoric uncertainties as learned loss attenuation. This technical report presents a comprehensive evaluation of the probabilistic suffix prediction approach's predictive performance and calibration under three different hyperparameter settings, using four real-life and one artificial event log. The results show that: i) probabilistic suffix prediction can outperform most likely suffix prediction, the U-ED-LSTM has reasonable predictive performance, and ii) the model's predictions are well calibrated.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21339
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Uncertainty-Aware ED-LSTM for Probabilistic Suffix Prediction
Mustroph, Henryk
Kunkler, Michel
Rinderle-Ma, Stefanie
Machine Learning
Artificial Intelligence
Suffix prediction of business processes forecasts the remaining sequence of events until process completion. Current approaches focus on predicting the most likely suffix, representing a single scenario. However, when the future course of a process is subject to uncertainty and high variability, the expressiveness of such a single scenario can be limited, since other possible scenarios, which together may have a higher overall probability, are overlooked. To address this limitation, we propose probabilistic suffix prediction, a novel approach that approximates a probability distribution of suffixes. The proposed approach is based on an Uncertainty-Aware Encoder-Decoder LSTM (U-ED-LSTM) and a Monte Carlo (MC) suffix sampling algorithm. We capture epistemic uncertainties via MC dropout and aleatoric uncertainties as learned loss attenuation. This technical report presents a comprehensive evaluation of the probabilistic suffix prediction approach's predictive performance and calibration under three different hyperparameter settings, using four real-life and one artificial event log. The results show that: i) probabilistic suffix prediction can outperform most likely suffix prediction, the U-ED-LSTM has reasonable predictive performance, and ii) the model's predictions are well calibrated.
title An Uncertainty-Aware ED-LSTM for Probabilistic Suffix Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.21339