Measuring competitiveness with data-driven principal component analysis: a case study of Chinese international construction companies

Abstract

Purpose

Defining and measuring competitiveness has been a major focus in the business and competition literature over the past decades. The paper aims to use data-driven principal component analysis (PCA) to measure firm competitiveness.

Design/methodology/approach

A “3Ps” (performance, potential, and process) firm competitiveness indicator system is structured for indicator selection. Data-driven PCA is proposed to measure competitiveness by reducing the dimensionality of indicators and assigning weights according to the endogenous structure of a dataset. To illustrate and validate the method, a case study applying to Chinese international construction companies (CICCs) was conducted.

Findings

In the case study, 4 principal components were derived from 11 indicators through PCA. The principal components were labeled as “performance” and “capability” under the two respective super-components of “profitability” and “solvency” of a company. Weights of 11 indicators were then generated and competitiveness of CICCs was finally calculated by composite indexes.

Research limitations/implications

This study offers a systematic indicator framework for firm competitiveness. The study also provides an alternative approach to better solve the problem of firm competitiveness measurement that has long plagued researchers.

Originality/value

The data-driven PCA approach alleviates the difficulties of dimensionality and subjectivity in measuring firm competitiveness and offers an alternative choice for companies and researchers to evaluate business success in future studies.

Citation

Guo, H. and Lu, W. (2023), "Measuring competitiveness with data-driven principal component analysis: a case study of Chinese international construction companies", Engineering, Construction and Architectural Management, Vol. 30 No. 4, pp. 1558-1577. https://doi.org/10.1108/ECAM-04-2020-0262