Data Science Application on Six Sigma: Global Survey Findings

Purpose – The Six Sigma (SS) program is a successful improvement initiative adopted by organizations worldwide. The digitalization of companies has led to a significant increase in data generation, which requires processing and analysis. Adapting to this data variety and complexity represents a challenge for SS, as its techniques developed in an era of data scarcity prove inadequate in the current context. Several studies suggest re-examining SS and incorporating new knowledge, especially techniques from Data Science (DS). This study aims to identify the most promising DS analytical techniques for SS projects and determine the most suitable ones for inclusion in SS training programs.
Design/methodology/approach – An online survey collected responses from 348 SS experts from 49 countries evaluating the applicability of DS techniques in SS. The analysis of the collected data included exploratory techniques and hypothesis testing.
Findings – The sector in which the experts work significantly influenced their assessments. Service, sales, and marketing professionals shared similar evaluations, distinct from those in industrial and cross-functional sectors. As a result, it is recommended to design two distinct training programs covering different analytical techniques suitable for each audience.
Originality/value – This study is the first to empirically assess the application of DS techniques in SS through a global survey. Moreover, it delineates the optimal training for SS specialists based on their activity sector, ensuring they gain essential skills to extract valuable insights from data-rich Industry 4.0 environments.

Six Sigma, Data Science, Industry 4.0, Digital age,