Generative Artificial Intelligence (GenAI) is spreading rapidly across organizational workflows, yet its systematic integration within Lean Six Sigma (LSS) has received limited scholarly attention. This paper maps selected GenAI technologies onto the five phases of the Define, Measure, Analyze, Improve, and Control (DMAIC) cycle. Building on evidence from adjacent fields, the work identifies and adapts promising use cases for core LSS tools: automated Voice of the Customer (VOC) analysis powered by Retrieval-Augmented Generation (RAG), knowledge-graph-driven Root Cause Analysis (RCA), and autonomous Artificial Intelligence (AI) agents supporting statistical analysis. The paper constructs a structured correspondence between GenAI capabilities and each DMAIC phase, articulating anticipated operational benefits, implementation considerations, and open research gaps. Rather than offering empirical validation, the work proposes theoretically grounded application scenarios and sets out a research agenda to guide future experimental and industrial investigations.
Fiocco, E., Proietti, S., Cesarotti, V. (2026). Integrating Generative AI into Lean Six Sigma: A Conceptual Framework for DMAIC Enhancement. ??????? it.cilea.surplus.oa.citation.tipologie.CitationProceedings.prensentedAt ??????? International Scientific Conference on Economics & Management (EMAN) 2026, Oxford, UK.
Integrating Generative AI into Lean Six Sigma: A Conceptual Framework for DMAIC Enhancement
Fiocco, Emanuele;Proietti, Serena;Cesarotti, Vittorio
2026-01-01
Abstract
Generative Artificial Intelligence (GenAI) is spreading rapidly across organizational workflows, yet its systematic integration within Lean Six Sigma (LSS) has received limited scholarly attention. This paper maps selected GenAI technologies onto the five phases of the Define, Measure, Analyze, Improve, and Control (DMAIC) cycle. Building on evidence from adjacent fields, the work identifies and adapts promising use cases for core LSS tools: automated Voice of the Customer (VOC) analysis powered by Retrieval-Augmented Generation (RAG), knowledge-graph-driven Root Cause Analysis (RCA), and autonomous Artificial Intelligence (AI) agents supporting statistical analysis. The paper constructs a structured correspondence between GenAI capabilities and each DMAIC phase, articulating anticipated operational benefits, implementation considerations, and open research gaps. Rather than offering empirical validation, the work proposes theoretically grounded application scenarios and sets out a research agenda to guide future experimental and industrial investigations.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


