PDM is an outcome-oriented predictive business process monitoring method for predictive deviation monitoring using conformance checking and deep learning.
If you use our code or fragments of it, please cite our paper:
@proceedings{weinzierl2021pdm,
title={Predictive Business Process Deviation Monitoring},
author={Sven Weinzierl and Sebastian Dunzer and Johannes Tenschert and Sandra Zilker and Martin Matzner},
booktitle={Proceedings of the 29th European Conference on Information Systems (ECIS2021)},
year={2021}
}
- Install Miniconda (https://docs.conda.io/en/latest/miniconda.html)
- After setting up miniconda you can make use of the
conda
command in your command line (e.g. CMD or Bash) - To quickly install the
pdm
package, runpip install -e .
inside the root directory. - To install required packages run
pip install -r requirements.txt
inside the root directory. - Set parameters in
config.py
- Train and test the Bi-LSTM models for the next activity prediction by executing
runner.py