Lean Six Sigma and Design of Experiments: An Empirical Case Study From the Dairy Industry

In today's highly competitive business environments, fast-paced, flexible and dynamic strategies are adopted to preserve sustainability that remains the center of attention of all organizations. To achieve such long-term objective, business intelligence plays a vital role in transforming big data into knowledge to support all sorts of business decisions at strategic, tactical and operational levels. In this context, emerging data analytics technologies are being widely implemented nowadays as their integration suggests intriguing solutions that can lead businesses' sustainability strategies. Advanced analytics is a semi-autonomous or autonomous examination of data using sophisticated tools in order to discover new insights and generate accurate and valid outcomes. This paper portrays the four main types of data analytics encompassing the descriptive, diagnostic, predictive and prescriptive analysis procedures. Furthermore, this research focuses on one of the predictive analysis tools, known as lean six sigma methodology and the design of experiments. A case study applied in a dairy industry shows the effectiveness and accuracy of such an advanced modeling and optimization technique. In fact, response surface methodology was applied to obtain the highest product's quality while optimizing steam pressure and conveyor speed, the factors that were proven to highly affect the labeling process of milk bottles. The findings of the present study showed that at a speed of 125 bottles/min and by applying 0.77 bar of steam pressure, the optimal results of multiple response variables were achieved. These results provide interesting insights to managers in the dairy industry and pave the way for other researchers to discover the efficient and impactful adoption of lean six sigma approaches in other industries, especially to solve complex optimization models.