Fuzzy MCDM approach to R&D project evaluation in Taiwan's public sectors

Abstract

Purpose

Establishing a performance‐oriented evaluation in public sectors is the key to successful administrations. However, because of lacking relative comparable measuring standards, it is difficult to measure the relative performance of one unit while comparing to other units with regard to the multiple criteria decision making (MCDM) of performance evaluation. This paper aims to focus on the performance ranking of research and development (R&D) projects in Taiwan's public sectors.

Design/methodology/approach

The algorithm in this paper is based on the concept of fuzzy set theory and the hierarchical structure analysis. The analyzing method adopts the methods of standard normal distribution, linear transformation, and fuzzy MCDM, carrying on the analysis of multiple criteria of the performance evaluation.

Findings

This paper constructs linguistic values to the subjective judgments and analyzes the ranking results of the performance evaluation with respect to 45 R&D projects of one of Taiwan's electric power companies. Thus, the paper demonstrates a successful way of evaluating R&D projects in the public sector.

Originality/value

In this paper, a decision algorithm based on the fuzzy set theory is proposed to solve the performance evaluation of R&D projects in public sectors. In order to solve the difficulties of measuring one unit of the relative performance of quantitative criteria comparing to the other units, the method of standard normal distribution is adopted while measuring the quantitative criteria. The concept of linguistic values and fuzzy numbers are used in this paper since they could easily be used to describe the subjective measurement of the appropriateness of alternatives and the importance weightings of criteria.

Citation

Lai, W., Chang, P. and Chou, Y. (2010), "Fuzzy MCDM approach to R&D project evaluation in Taiwan's public sectors", Journal of Technology Management in China, Vol. 5 No. 1, pp. 84-101. https://doi.org/10.1108/17468771011032822