Advancing sustainable operational excellence: a machine learning approach for emerging economies
Purpose This research introduces a novel methodology that leverages machine learning (ML), specifically the k-means clustering algorithm, to assess operational excellence (OE) maturity levels in companies within emerging economies. The study aims to identify and classify stages of OE maturity to support sustainable development initiatives. Design/methodology/approach The study draws on data from a comprehensive survey of 106 companies spanning various sectors in Latin America, capturing qualitative insights on OE practices. The k-means algorithm was applied to classify companies into distinct OE maturity stages. This innovative approach provides a novel perspective on sustainable business growth and management in emerging markets. Findings The analysis highlights considerable variation in OE maturity levels among the surveyed companies, with larger firms generally exhibiting higher maturity. The k-means clustering classified companies into five maturity stages, ranging from “Basic” to “Champion.” This classification provides a framework for understanding the evolution of OE practices and their influence on sustainable development. Research limitations/implications The study’s focus on Latin America may limit its generalizability to other regions. Additionally, the use of qualitative survey data introduces subjectivity, which could influence the clustering outcomes. Practical implications The findings emphasize the role of OE in advancing sustainable business practices. By categorizing companies based on OE maturity, decision-makers can tailor strategies to enhance sustainability and operational efficiency, particularly in emerging economies. Originality/value The study introduces a machine learning-based approach to assess OE maturity in emerging markets, contributing to the discourse on sustainable development and operational excellence. This research offers practical insights for organizations seeking to improve their OE practices and achieve sustainability goals.
Authors
- Andrés Muñoz‐Villamizar (ORCID: https://orcid.org/0000-0003-2542-0645)
- Javier Santos (ORCID: https://orcid.org/0000-0001-7612-0533)
- Rafael Henriquez-Machado (ORCID: https://orcid.org/0000-0001-6225-2148)
Institutions
- Universidad de La Sabana (CO)
- Universidad de Navarra (ES)
Publication Details
- Journal
- International Journal of Productivity and Performance Management
- Published
- 2025-04-07
- DOI
- https://doi.org/10.1108/ijppm-05-2024-0332
- Citations
- 1
- Primary Topic
- Big Data and Business Intelligence
- Type
- article
- Field-Weighted Citation Impact
- 2.28