In System Alignments we Trust! Explainable Alignments via Projections

2025-01-24

AI Summary

In complex business processes involving multiple entities, alignment between event logs and process models becomes unreliable due to partial incompleteness or distortion in either source. Method: This paper proposes a projection-based relaxed alignment method, the first to integrate projection transformations and relaxation optimization into the process mining framework. It introduces an interpretable, projection-driven relaxation mechanism that explicitly distinguishes trustworthy from untrustworthy segments in both logs and models, enabling multi-dimensional modeling of entity interactions. Contribution/Results: Compared to classical alignment algorithms, the method significantly improves robustness and interpretability under incomplete and noisy data. Empirical evaluation on multiple real-world process datasets demonstrates its effectiveness in identifying quality defects. The approach establishes a novel paradigm for process understanding and trustworthy diagnostic analysis.

Technology Category

• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Reasoning under Uncertainty: Relational Probabilistic Models
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Alignments are a well-known process mining technique for reconciling system logs and normative process models. Evidence of certain behaviors in a real system may only be present in one representation - either a log or a model - but not in the other. Since for processes in which multiple entities, like objects and resources, are involved in the activities, their interactions affect the behavior and are therefore essential to take into account in the alignments. Additionally, both logged and modeled representations of reality may be imprecise and only partially represent some of these entities, but not all. In this paper, we introduce the concept of"relaxations"through projections for alignments to deal with partially correct models and logs. Relaxed alignments help to distinguish between trustworthy and untrustworthy content of the two representations (the log and the model) to achieve a better understanding of the underlying process and expose quality issues.

Problem

• Process Alignment
• Complex Interactions
• Information Incompleteness

Innovation

• Relaxation Alignment
• Projection Method
• Process Execution Analysis