Integration of Data Envelopment Analysis and Clustering Methods Academic Article uri icon

abstract

  • Data Envelopment Analysis (DEA) has been applied creatively in various study domains to compare and evaluate different Decision Making Units (DMUs) based on multiple inputoutput attributes. In this paper, the performance of Jordanian public hospitals is assessed via a methodology combining DEA with data mining methods, specifically, clustering. Initially, inputs of inefficient hospitals were altered to check for waste in the allocated resources. Then, the number of inputsoutputs was manipulated to test if the number is strongly influencing the productivity of the DMUs. The number of DMUs used was 27 public hospitals and the applicable efficiency measurements used were constant return to scale (CRS) and variable return to scale (VRS) through the DEAP software. Experiments showed that the efficiency of a hospital might be more meaningfully assessed if it is compared with a group of hospitals that are similar in some factors. More specifically, results of applying the CRS model proved that 77% of the hospitals were efficient. Additionally, we found that the inefficiencies of some hospitals are linked to weak resource utilization. It is concluded that number of inputsoutputs inserted in the efficiency evaluation process impacts the resulted values.

published proceedings

  • JOURNAL OF INFORMATION & KNOWLEDGE MANAGEMENT

author list (cited authors)

  • Najadat, H., Alaiad, A., Abu Alasal, S., Mrayyan, G. A., & Alsmadi, I.

citation count

  • 4

complete list of authors

  • Najadat, Hassan||Alaiad, Ahmad||Abu Alasal, Sanaa||Mrayyan, Ghadeer Anwar||Alsmadi, Izzat

publication date

  • March 2020