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

TL;DR

Manual value-added analysis of business processes is time-consuming and subjective. The authors propose a two-phase, LLM-based framework consisting of Activity Breakdown and Value-Added Analysis, powered by structured prompts and greedy prompt optimization, and evaluated on 50 publicly available BPMN processes with ground-truth annotations. The study demonstrates that structured prompting improves alignment with human judgments and enables scalable qualitative waste identification, with the LEAN Analyst configuration particularly effective at detecting non-value-added steps while maintaining overall performance. The work advocates a human‑in‑the‑loop use, discusses practical implications and ethical considerations, and outlines future directions such as incorporating event logs and automated prompt tuning to extend to process redesign.

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.

Figures (4)

• Figure 1: Overview of our LLM-based value-added analysis illustrated on an excerpt of a rental equipment process (top; dumas2018fundamentals). The first two activities (left) are broken down into multiple steps (center), which are then labeled as value adding (VA), business value adding (BVA) or non-value adding (NVA) (right).
• Figure 2: The final prompt used to obtain an activity breakdown from our LLM.
• Figure 3: The final prompt for value-adding analysis.
• Figure 4: Confusion matrix for the LEAN Expert (Detailed) configuration on the test set.