An Uncertainty-Aware ED-LSTM for Probabilistic Suffix Prediction

2025-05-27

AI Summary

To address the limitation of deterministic suffix prediction in business process mining—its inability to capture inherent future uncertainty—this paper proposes the first probabilistic suffix prediction framework, which models the full probability distribution over possible suffix sequences. Methodologically, we introduce the U-ED-LSTM architecture, the first to jointly integrate Monte Carlo Dropout (to quantify epistemic uncertainty) and learnable loss attenuation (to model aleatoric uncertainty), and propose a Monte Carlo suffix sampling algorithm enabling calibrated probabilistic predictions. Experiments on four real-world event logs demonstrate that the framework’s probabilistic prediction mean significantly outperforms conventional most-likely-suffix baselines—especially under sparse prefixes and long suffixes—while its uncertainty estimates exhibit strong calibration, as validated by standard metrics such as expected calibration error.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Probabilistic Programming
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Suffix prediction of business processes forecasts the remaining sequence of events until process completion. Current approaches focus on predicting a single, most likely suffix. However, if the future course of a process is exposed to uncertainty or has high variability, the expressiveness of a single suffix prediction can be limited. 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 provides a detailed evaluation of the U-ED-LSTM's predictive performance and assesses its calibration on four real-life event logs with three different hyperparameter settings. The results show that i) the U-ED-LSTM has reasonable predictive performance across various datasets, ii) aggregating probabilistic suffix predictions into mean values can outperform most likely predictions, particularly for rare prefixes or longer suffixes, and iii) the approach effectively captures uncertainties present in event logs.

Problem

• Predicts remaining business process events probabilistically
• Addresses uncertainty in process suffix prediction
• Combines epistemic and aleatoric uncertainty modeling

Innovation

• Uses Uncertainty-Aware Encoder-Decoder LSTM
• Incorporates Monte Carlo suffix sampling
• Learns epistemic and aleatoric uncertainties