SPICE框架让流程预测模型可复现，统一对比不同算法表现。
Towards Reproducibility in Predictive Process Mining: SPICE -- A Deep Learning Library
- 用PyTorch重实现3种主流深度学习流程预测方法
- 在11个数据集上验证，与原始结果一致且可公平比较
- 提供可配置接口，适合研究者复现与新模型测试
近年来，基于人工神经网络的预测性流程挖掘（PPM）技术已成为监控未完成业务流程未来行为和预测关键绩效指标（KPI）的重要方法。然而，许多PPM方法存在可复现性差、决策过程不透明、难以整合新数据集及基准测试的问题，导致不同实现之间的比较极为困难。本文提出SPICE，一个基于Python的框架，在PyTorch中重实现了三种流行的基于深度学习的PPM基线方法，并设计了通用基础架构，具备严格的可配置性，以实现过去与未来建模方法的可复现、稳健比较。我们在11个数据集上将SPICE与原始报告指标及公平指标进行对比，验证其有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。