Comprehensive Attribute Encoding and Dynamic LSTM HyperModels for Outcome Oriented Predictive Business Process Monitoring

TL;DR

This paper introduces dynamic LSTM HyperModels with hierarchical encoding and pseudo-embedding techniques to improve outcome prediction in complex, real-world business process monitoring scenarios, addressing challenges like event simultaneity and class imbalance.

Contribution

It presents a novel suite of adaptable LSTM-based models with hierarchical and character-based encoding, enhancing flexibility and generalization in predictive business process monitoring.

Findings

Achieved up to 100% accuracy on balanced datasets

F1 scores exceeded 86% on imbalanced datasets

Demonstrated effectiveness across four diverse datasets

Abstract

Predictive Business Process Monitoring (PBPM) aims to forecast future outcomes of ongoing business processes. However, existing methods often lack flexibility to handle real-world challenges such as simultaneous events, class imbalance, and multi-level attributes. While prior work has explored static encoding schemes and fixed LSTM architectures, they struggle to support adaptive representations and generalize across heterogeneous datasets. To address these limitations, we propose a suite of dynamic LSTM HyperModels that integrate two-level hierarchical encoding for event and sequence attributes, character-based decomposition of event labels, and novel pseudo-embedding techniques for durations and attribute correlations. We further introduce specialized LSTM variants for simultaneous event modeling, leveraging multidimensional embeddings and time-difference flag augmentation. Experimental validation on four public and real-world datasets demonstrates up to 100% accuracy on balanced datasets and F1 scores exceeding 86\% on imbalanced ones. Our approach advances PBPM by offering modular and interpretable models better suited for deployment in complex settings. Beyond PBPM, it contributes to the broader AI community by improving temporal outcome prediction, supporting data heterogeneity, and promoting explainable process intelligence frameworks.