Exploratory Benchmarking with DEA and Multidimensional Scaling - Process and Reference Model
Steffen Hoffmann
Wissenschaftliche Vorträge
Data Envelopment Analysis
International Conference on Data Envelopment Analysis, September 4-6, 2023, University of Surrey Guildford.

Benchmarking is a valuable process to improve strategic as well as operational decisions in profit and nonprofit organizations. An important subprocess of benchmarking relates to measuring performance gaps and uncovering their causes. While Data Envelopment Analysis (DEA) may handle the part of evaluation, Data Mining tasks are appropriate to explore the link of computational results with additional knowledge. Therefore, a new Data Mining process – called Exploratory Benchmarking – is proposed that integrates DEA and Multidimensional Scaling (MDS) as a reference model to structure decision support by applying well-researched methods. The process is exemplified by a real-world application in the field of service operations. However, the approach may be adopted far beyond as a standard process in business analytics and consulting.