Predictive Business Process Monitoring with LSTM Neural Networks

TL;DR

This paper demonstrates that LSTM neural networks can be effectively used for various predictive business process monitoring tasks, outperforming existing methods in accuracy and versatility across different prediction scenarios.

Contribution

The paper introduces an LSTM-based approach that provides consistently accurate predictions for multiple process monitoring tasks, reducing the need for task-specific tuning.

Findings

LSTMs outperform existing techniques in next event and timestamp prediction

LSTMs effectively predict full case continuations

LSTMs outperform tailor-made methods in remaining time prediction

Abstract

Predictive business process monitoring methods exploit logs of completed cases of a process in order to make predictions about running cases thereof. Existing methods in this space are tailor-made for specific prediction tasks. Moreover, their relative accuracy is highly sensitive to the dataset at hand, thus requiring users to engage in trial-and-error and tuning when applying them in a specific setting. This paper investigates Long Short-Term Memory (LSTM) neural networks as an approach to build consistently accurate models for a wide range of predictive process monitoring tasks. First, we show that LSTMs outperform existing techniques to predict the next event of a running case and its timestamp. Next, we show how to use models for predicting the next task in order to predict the full continuation of a running case. Finally, we apply the same approach to predict the remaining time, and show that this approach outperforms existing tailor-made methods.