Enhancing Lean Management with explainable AI: a framework for transparency, efficiency and empowerment

Abstract

Purpose The objective of this research is to create a model that mixes Explainable Artificial Intelligence (XAI) with Lean Management. This combination is expected to increase the transparency and overall efficiency of operations and involve employees more in the decision-making process. Design/methodology/approach The research uses SHAP and LIME and aligns their interpretability with Lean principles. Predictive maintenance and quality control are used as examples to illustrate the framework and show how XAI outputs can direct Lean continuous improvement. Findings By integrating XAI with Lean, the AI “black-box” problem is significantly reduced since the model provides clear, data-driven insights. This approach not only increases the level of participation from employees but also leads to better operational performance and supports the Lean practices of eliminating waste and creating value. Research limitations/implications The proposed model is a theoretical one that must be tested empirically in various industries before it can be considered practically applicable. Besides, other XAI techniques should be included in the validation process to examine the issue of long-term outcomes as well. Practical implications The managers can implement the suggested framework to convert AI results into actions that not only are transparent but also are in line with the company's AI and Lean practices, thereby continuously providing the organization with value through learning. Originality/value This research sets the stage for the future of Industry 4.0 by depicting a well-structured connection between Lean Management and XAI that facilitates the human-centered path toward responsible AI adoption.

Ähnliche Arbeiten