A data envelopment analysis model with resource reallocation decisions and production output prediction

• Main Author: Tan, Martha Lauren L.
• Format: text
• Language: English
• Published: Animo Repository 2009
• Subjects: Data envelopment analysis; Production planning; Benchmarking; Operations Research, Systems Engineering and Industrial Engineering
• Online Access: https://animorepository.dlsu.edu.ph/etd_masteral/3828; https://animorepository.dlsu.edu.ph/context/etd_masteral/article/10666/viewcontent/CDTG004679_P.pdf
• Institution: De La Salle University

Benchmarking is a commonly used approach to performance improvement in both manufacturing and services, particularly in public services. In theory best practice benchmarking involves: the identification of areas of organizational performance that require improvement, through comparison with relevant better performers; the identification of sources of detailed ideas about how to enact those improvements; and the implementation of change. In most benchmarking literature however, focus has been put on performance measurement and little has been done on the development of benchmarking tools in aiding performance improvement decisions. Through benchmarking techniques, excessive usage of inputs can be identified and targets can be set to reduce these surpluses. However, benchmarking should go beyond just identifying targets; benchmarking should be able to help provide insights on how resources can be distributed to achieve the most potential. It is important to know which areas to attack to improve performance as there is some kind of relationship between resource utilization and resource allocation (Minwir, 1999). This paper suggests that concepts in Data Envelopment Analysis (DEA), a tool increasingly used in benchmarking, can be further used in helping decision makers in improving overall organizational performance through reallocating resources. This can be achieved through identifying input surpluses and reallocating the input surpluses with the aid of a reallocation model with output prediction. Through the development and combination of an aggregate DEA model and a forecast model, a reallocation model was formulated. Through validation and sensitivity of the model, this study was able to show how benchmarking comparative analysis results can be used to guide decisions in improving the overall system performance. With current inputs used, output can still be improved by identifying input surpluses in each Decision Making Unit (DMU) and reallocating the resources to other DMUs that can realize the most potential in iv terms of output. This paper showcased how output prediction can help in the decisions in allocating resources to DMUs. Allocating resources to efficient units only does not always show the highest return. Being able to predict how much an increase in input will increase output can help decision makers realize the most potential in the resources being allocated.