Self-Explaining Neural Networks for Business Process Monitoring

2025-03-23

AI Summary

Predictive Business Process Monitoring (PBPM) relies heavily on sequence models like LSTMs, yet their lack of interpretability hinders trust and adoption; existing post-hoc explanation methods suffer from low fidelity, high computational overhead, and poor generalizability. Method: We propose the first end-to-end self-explaining LSTM architecture specifically designed for PBPM. Unlike post-hoc approaches, our method explicitly integrates explanation generation into the training objective, jointly optimizing next-activity prediction loss and explanation fidelity constraints. Contribution/Results: Our approach achieves comparable—or even improved—prediction accuracy while significantly outperforming mainstream post-hoc methods (e.g., LIME, SHAP) in explanation fidelity. Moreover, it reduces inference latency by over an order of magnitude. Crucially, this work establishes the first unified modeling framework for PBPM that simultaneously ensures high-fidelity, lightweight, and intrinsic interpretability—where explanations are generated natively during training, not retroactively.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Tasks in Predictive Business Process Monitoring (PBPM), such as Next Activity Prediction, focus on generating useful business predictions from historical case logs. Recently, Deep Learning methods, particularly sequence-to-sequence models like Long Short-Term Memory (LSTM), have become a dominant approach for tackling these tasks. However, to enhance model transparency, build trust in the predictions, and gain a deeper understanding of business processes, it is crucial to explain the decisions made by these models. Existing explainability methods for PBPM decisions are typically *post-hoc*, meaning they provide explanations only after the model has been trained. Unfortunately, these post-hoc approaches have shown to face various challenges, including lack of faithfulness, high computational costs and a significant sensitivity to out-of-distribution samples. In this work, we introduce, to the best of our knowledge, the first *self-explaining neural network* architecture for predictive process monitoring. Our framework trains an LSTM model that not only provides predictions but also outputs a concise explanation for each prediction, while adapting the optimization objective to improve the reliability of the explanation. We first demonstrate that incorporating explainability into the training process does not hurt model performance, and in some cases, actually improves it. Additionally, we show that our method outperforms post-hoc approaches in terms of both the faithfulness of the generated explanations and substantial improvements in efficiency.

Problem

• Enhancing transparency in predictive business process monitoring.
• Overcoming limitations of post-hoc explainability methods in PBPM.
• Integrating self-explaining capabilities into LSTM models for PBPM.

Innovation

• Self-explaining LSTM for process monitoring
• Integrated explainability during model training
• Improved faithfulness and efficiency over post-hoc