Unlocking Sustainability Compliance: Characterizing the EU Taxonomy for Business Process Management

TL;DR

This paper investigates whether the EU taxonomy for sustainable activities can be operationalized for automatic conformance checking in business processes. It introduces a three-stage pipeline that uses few-shot learning with a large language model to characterize taxonomy constraints by process dimensions (control-flow, time, resources, data) and data requirements, enabling data-driven regulatory compliance monitoring. Empirical results show that a substantial portion of taxonomy constraints (notably in energy, manufacturing, transport, and water) can be captured as process constraints, with the majority focusing on control-flow and data aspects; about 80% of identified constraints appear amenable to conformance checking, while others require manual expert input. The study lays groundwork for automatic taxonomy-alignment monitoring, informs data-capture needs for event logs, and offers a starting point for applying similar constraint-characterization pipelines to other regulatory frameworks, with future work including real-world deployment and refinement of prescriptive models including minimum safeguards.

Abstract

To promote sustainable business practices, and to achieve climate neutrality by 2050, the EU has developed the taxonomy of sustainable activities, which describes when exactly business practices can be considered sustainable. While the taxonomy has only been recently established, progressively more companies will have to report how much of their revenue was created via sustainably executed business processes. To help companies prepare to assess whether their business processes comply with the constraints outlined in the taxonomy, we investigate in how far these criteria can be used for conformance checking, that is, assessing in a data-driven manner, whether business process executions adhere to regulatory constraints. For this, we develop a few-shot learning pipeline to characterize the constraints of the taxonomy with the help of an LLM as to the process dimensions they relate to. We find that many constraints of the taxonomy are useable for conformance checking, particularly in the sectors of energy, manufacturing, and transport. This will aid companies in preparing to monitor regulatory compliance with the taxonomy automatically, by characterizing what kind of information they need to extract, and by providing a better understanding of sectors where such an assessment is feasible and where it is not.

Figures (5)

• Figure 1: Conceptual overview of compliance monitoring with conformance checking carmonaConformanceCheckingRelating2018klessascheckReviewingConformance2024
• Figure 2: Schematic overview of the EU taxonomy for sustainable activities and its concepts, derived from europeancommissionEUTaxonomySustainableeuropeancommissionUserGuideNavigate2023
• Figure 3: Schematic overview of the taxonomy constraint characterization pipeline
• Figure 4: Constraint types per industry sector across all environmental objectives and screening criteria
• Figure 5: Number of constraints per type and environmental objective