Deep Learning Process Prediction with Discrete and Continuous Data Features

Stefan Schönig, Richard Jasinski, Lars Ackermann, Stefan Jablonski

2018

Abstract

Process prediction is a well known method to support participants in performing business processes. These methods use event logs of executed cases as a knowledge base to make predictions for running instances. A range of such techniques have been proposed for different tasks, e.g., for predicting the next activity or the remaining time of a running instance. Neural networks with Long Short-Term Memory architectures have turned out to be highly customizable and precise in predicting the next activity in a running case. Current research, however, focuses on the prediction of future activities using activity labels and resource information while further event log information, in particular discrete and continuous event data is neglected. In this paper, we show how prediction accuracy can significantly be improved by incorporating event data attributes. We regard this extension of conventional algorithms as a substantial contribution to the field of activity prediction. The new approach has been validated with a recent real-life event log.

Paper Citation

in Harvard Style

Schönig S., Jasinski R., Ackermann L. and Jablonski S. (2018). Deep Learning Process Prediction with Discrete and Continuous Data Features.In Proceedings of the 13th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE, ISBN 978-989-758-300-1, pages 314-319. DOI: 10.5220/0006772003140319

in Bibtex Style

@conference{enase18,
author={Stefan Schönig and Richard Jasinski and Lars Ackermann and Stefan Jablonski},
title={Deep Learning Process Prediction with Discrete and Continuous Data Features},
booktitle={Proceedings of the 13th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE,},
year={2018},
pages={314-319},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006772003140319},
isbn={978-989-758-300-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE,
TI - Deep Learning Process Prediction with Discrete and Continuous Data Features
SN - 978-989-758-300-1
AU - Schönig S.
AU - Jasinski R.
AU - Ackermann L.
AU - Jablonski S.
PY - 2018
SP - 314
EP - 319
DO - 10.5220/0006772003140319