Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Predictive Analysis of Business Processes Using Neural Networks with Attention Mechanism

: Philipp, Patrick; Jacob, Ruben; Robert, Sebastian; Beyerer, Jürgen


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
ICAIIC 2020, 2nd International Conference on Artificial Intelligence in Information and Communication : 19-21 February 2020, Fukuoka, Japan
Piscataway, NJ: IEEE, 2020
ISBN: 978-1-7281-4985-1
ISBN: 978-1-7281-4986-8
International Conference on Artificial Intelligence in Information and Communication (ICAIIC) <2, 2020, Fukuoka>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
Artificial Intelligence for the Review of Workflows
Conference Paper
Fraunhofer IOSB ()
process prediction; deep learning; neural networks; attention mechanism; transformer

The analysis of ongoing processes is an important task in business process management. This is not surprising, since (e.g.) being able to predict future events in processes enables companies to intervene at an early stage if deviations from a desired workflow are likely to occur. Subsequently, errors and associated financial losses can be prevented or avoided. A common basis for being able to predict future events is a sequence of previous events that are typically stored in a so called event log. In this work we present a neural network with attention mechanism, which is trained using publicly available event logs (e.g. BPI Challenge 2013). Furthermore, we elaborate the proposed model with an extensive dataset of events of a worldwide known German software company. In addition to promising results (e.g.) with regard to n-gram models, the training time of the proposed model is shorter than that of typical reference models such as neural networks with a longshort-term memory architecture (LSTM).