In recent years, Predictive Process Mining (PPM) techniques based on artificial neural networks have evolved as a method for monitoring the future behavior of unfolding business processes and predicting Key Performance Indicators (KPIs). However, many PPM approaches often lack reproducibility, transparency in decision making, usability for incorporating novel datasets and benchmarking, making comparisons among different implementations very difficult. In this paper, we propose SPICE, a Python framework that reimplements three popular, existing baseline deep-learning-based methods for PPM in PyTorch, while designing a common base framework with rigorous configurability to enable reproducible and robust comparison of past and future modelling approaches. We compare SPICE to original reported metrics and with fair metrics on 11 datasets.
@article{arxiv.2512.16715,
title = {Towards Reproducibility in Predictive Process Mining: SPICE -- A Deep Learning Library},
author = {Oliver Stritzel and Nick Hühnerbein and Simon Rauch and Itzel Zarate and Lukas Fleischmann and Moike Buck and Attila Lischka and Christian Frey},
journal= {arXiv preprint arXiv:2512.16715},
year = {2025}
}