Development of a Kaizen framework through Machine learning methodologies​: the case study of San Benedetto

This thesis presents the application of data analysis and machine learning techniques within a Lean Manufacturing framework, focusing on a Kaizen improvement project at Acqua Minerale San Benedetto S.p.A. The objective is to enhance production line performance through systematic monitoring and continuous improvement, using Overall Equipment Effectiveness (OEE) as the main performance indicator. Machine learning methods, such as Principal Component Analysis (PCA), combined with statistical analysis, were applied to identify inefficiencies, support process monitoring, and strengthen decision-making. The integration of these data-driven approaches into Lean practices improved the ability to follow the process, anticipate bottlenecks, resulting in measurable improvements in productivity and equipment utilization.