Using Data Envelopment Analysis to benchmark logistic performance in Belgian manufacturing companies

Performance evaluation and benchmarking are widely used methods to identify and adopt best practices as a means to improve performance and increase productivity, and are particularly valuable when no objective or engineered standard is available to define efficient and effective performance. DEA is a linear programming technique used to evaluate the efficiency of decision-making units (DMUs) where multiple inputs and outputs are involved. The main idea of DEA is to extend the traditional concept of productivity or efficiency (ratio of output and input) to make it suitable for the multiple-input multiple-output case. We will use the Excel implementations introduced in Zhu, J., (2003), to study a set of data from 80 Belgium companies that includes some logistic measurements, general information and best practices adoption rates. The aim of this work is to discuss the ways DEA can be useful in benchmarking, and, in an effort to address the unique needs of SMEs to develop easy-to-understand, graphical ways to display the analyses' results.