A HIERARCHICAL PEOPLE-CENTRIC OPERATIONAL EXCELLENCE PERFORMANCE MEASUREMENT SYSTEM TO CREATE AN INTELLIGENT DECISION-MAKING PROCESS IN MANUFACTURING INDUSTRIES

This research aims to enhance manufacturing industry decision-making processes by developing and utilizing a hierarchical Performance Measurement System (PMS) comprising a statistical predictive model. The literature gaps were addressed in three ways. First, indicators are categorized into people, material, equipment, and information-related categories and organized into a hierarchical structure. Interdependencies between these indicators are fully mapped and quantified using multiple regression analysis, validated through canonical correlation analysis, and confirmed through a nuclear power facility case study. Second, the research further investigates the correlation and impact between different categories of indicators, with a particular focus on understanding the influence of people-related metrics on overall performance. To achieve these objectives, the study employs advanced statistical methods, including partial least squares regression, to identify the optimal components of the PMS and develop accurate models that inform decision-making and canonical correlation analysis to identify vertical integration between the categories. Third, statistical predictive models that can anticipate the impact of a strategy on performance and people indicators are developed and their performance is assessed. Through the application of causality analysis, the optimal model can discern and identify the most influential group of leading and lagging indicators that contribute to a strategic metric, irrespective of whether it is driven by personnel or processes. The research framework is then tested using indicators from a stochastic people-driven system from a top-quality marine canvas manufacturing company.