An Uncertainty-Aware ED-LSTM for Probabilistic Suffix Prediction

TL;DR

This paper introduces a probabilistic suffix prediction method for business process forecasting using an Uncertainty-Aware Encoder-Decoder LSTM, capturing uncertainties to improve prediction quality and calibration.

Contribution

It presents a novel probabilistic suffix prediction approach with an Uncertainty-Aware ED-LSTM, addressing limitations of single-scenario predictions in uncertain, variable processes.

Findings

Probabilistic suffix prediction outperforms most likely suffix prediction.

U-ED-LSTM demonstrates reasonable predictive performance.

Predictions are well calibrated across different settings.

Abstract

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.