Automated Business Process Analysis: An LLM-Based Approach to Value Assessment

2025-04-09

AI Summary

Qualitative lean analysis of business process value addition is highly manual, time-consuming, and subjective. Method: This paper introduces large language models (LLMs) to qualitative lean analysis for the first time, proposing a two-stage structured framework: (1) automatic decomposition of high-level business activities into fine-grained operational steps; and (2) systematic classification of each step’s value-adding nature according to the lean value taxonomy. The method integrates zero-shot reasoning with interpretable, structured prompting to balance deep semantic understanding and transparent decision logic. Contribution/Results: Evaluated on 50 real-world business process models, the framework significantly outperforms zero-shot baselines in accurately identifying non-value-adding steps and systematically pinpointing waste sources. It extends the applicability of LLMs in process management and establishes a novel, low-human-effort, highly interpretable AI-assisted paradigm for process optimization.

Technology Category

Natural Language Processing: (Large) Language ModelsMachine Learning: Large Multimodal Models (LMMs)Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

Economics, Online Markets and Human Computation: Cost models of using LLMs in production systemsSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Business processes are fundamental to organizational operations, yet their optimization remains challenging due to the timeconsuming nature of manual process analysis. Our paper harnesses Large Language Models (LLMs) to automate value-added analysis, a qualitative process analysis technique that aims to identify steps in the process that do not deliver value. To date, this technique is predominantly manual, time-consuming, and subjective. Our method offers a more principled approach which operates in two phases: first, decomposing high-level activities into detailed steps to enable granular analysis, and second, performing a value-added analysis to classify each step according to Lean principles. This approach enables systematic identification of waste while maintaining the semantic understanding necessary for qualitative analysis. We develop our approach using 50 business process models, for which we collect and publish manual ground-truth labels. Our evaluation, comparing zero-shot baselines with more structured prompts reveals (a) a consistent benefit of structured prompting and (b) promising performance for both tasks. We discuss the potential for LLMs to augment human expertise in qualitative process analysis while reducing the time and subjectivity inherent in manual approaches.

Problem

• Automating value-added analysis in business processes using LLMs
• Reducing time and subjectivity in manual process analysis
• Classifying process steps for waste identification via Lean principles

Innovation

• LLMs automate value-added analysis in processes
• Two-phase method: decomposition and Lean classification
• Structured prompting improves performance consistently