LSTM Networks for Data-Aware Remaining Time Prediction of Business Process Instances
This work addresses the need for business managers to manage processes under service level agreements by providing timely predictions to prevent delays, though it appears incremental as it applies an existing method (LSTMs) to a specific domain.
The paper tackles the problem of predicting the completion time of business process instances by proposing an approach based on LSTM networks that leverages event data for accurate forecasts, with experiments on real-world datasets confirming its quality.
Predicting the completion time of business process instances would be a very helpful aid when managing processes under service level agreement constraints. The ability to know in advance the trend of running process instances would allow business managers to react in time, in order to prevent delays or undesirable situations. However, making such accurate forecasts is not easy: many factors may influence the required time to complete a process instance. In this paper, we propose an approach based on deep Recurrent Neural Networks (specifically LSTMs) that is able to exploit arbitrary information associated to single events, in order to produce an as-accurate-as-possible prediction of the completion time of running instances. Experiments on real-world datasets confirm the quality of our proposal.