processpredictR: Process Prediction

Means to predict process flow, such as process outcome, next activity, next time, remaining time, and remaining trace. Off-the-shelf predictive models based on the concept of Transformers are provided, as well as multiple ways to customize the models. This package is partly based on work described in Zaharah A. Bukhsh, Aaqib Saeed, & Remco M. Dijkman. (2021). "ProcessTransformer: Predictive Business Process Monitoring with Transformer Network" <arXiv:2104.00721>.

Version: 0.1.0
Depends: R (≥ 2.10)
Imports: bupaR, edeaR, dplyr, forcats, magrittr, reticulate, tidyr, tidyselect, purrr, stringr, keras, tensorflow, rlang, data.table, mltools, ggplot2, cli, glue, plotly, progress
Suggests: knitr, rmarkdown, lubridate, eventdataR
Published: 2023-01-17
Author: Ivan Esin [aut], Gert Janssenswillen [cre], Hasselt University [cph]
Maintainer: Gert Janssenswillen <gert.janssenswillen at uhasselt.be>
License: MIT + file LICENSE
NeedsCompilation: no
Materials: README
CRAN checks: processpredictR results

Documentation:

Reference manual: processpredictR.pdf
Vignettes: Introduction to processpredictR: workflow

Downloads:

Package source: processpredictR_0.1.0.tar.gz
Windows binaries: r-devel: processpredictR_0.1.0.zip, r-release: processpredictR_0.1.0.zip, r-oldrel: processpredictR_0.1.0.zip
macOS binaries: r-release (arm64): processpredictR_0.1.0.tgz, r-oldrel (arm64): processpredictR_0.1.0.tgz, r-release (x86_64): processpredictR_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=processpredictR to link to this page.