Open Access


Download data is not yet available.


This paper focuses on employing machine learning techniques to cluster politically affiliated groups. The study utilizes a sample of enterprises listed on the stock exchanges of Ho Chi Minh City and Hanoi, analyzing research data spanning the period from 2015 to 2020. The dataset comprises various variables, including the state ownership ratio, the level of political connections among business leaders, and financial indicators derived from the listed financial statements of these enterprises. In this study, the author measures political connections using the K-means algorithm and compares the results of the K-means clustering with the traditional manual method of assessing political connections, which involves assigning values of either 0 or 1. A value of 0 indicates no political affiliation, while a value of 1 represents political affiliation. Additionally, the author conducts three cluster analyses to gain deeper insights into the data. The findings of this research conclude that machine learning clustering using the K-means model holds promise in effectively identifying firms with political connections compared to the traditional manual approach. It is observed that politically connected businesses listed on the stock exchanges of Ho Chi Minh City and Hanoi reap numerous benefits in terms of investment activities, resource accessibility, and capital. However, the study also acknowledges the negative impact that such political affiliations can have on firm performance. Based on the results, the authors recommend maintaining a moderate degree of political affiliation, as this approach may assist firms in achieving better overall performance. By striking the right balance, companies can leverage the advantages of political connections while minimizing any adverse effects on their operations. In conclusion, this study highlights the potential of machine learning clustering, specifically utilizing the K-means algorithm, to effectively identify politically affiliated groups among enterprises listed on the stock exchanges of Ho Chi Minh City and Hanoi. The research emphasizes the benefits of political connections for businesses but also underscores the need for careful management to optimize performance outcomes.

Author's Affiliation
  • Phan Huy Tam

    Email I'd for correspondance: [email protected]
    Google Scholar Pubmed

  • Can Dinh Ngoc

    Google Scholar Pubmed

  • Tu Ta Thi Cam

    Google Scholar Pubmed

  • Tam Luong Thi My

    Google Scholar Pubmed

  • Hien Nguyen Thi Thuy

    Google Scholar Pubmed

  • Minh Ngo Hai

    Google Scholar Pubmed

Article Details

Issue: Vol 7 No 3 (2023): Vol 7 (3): Under publishing
Page No.: In press
Published: Oct 11, 2023
Section: Research article

 Copyright Info

Creative Commons License

Copyright: The Authors. This is an open access article distributed under the terms of the Creative Commons Attribution License CC-BY 4.0., which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

 How to Cite
Tam, P., Ngoc, C., Ta Thi Cam, T., Luong Thi My, T., Nguyen Thi Thuy, H., & Ngo Hai, M. (2023). Political affiliate clustering with machine learning in Vietnam stock exchange. VNUHCM Journal of Economics, Business and Law, 7(3), In press.

 Cited by

Article level Metrics by Paperbuzz/Impactstory
Article level Metrics by Altmetrics

 Article Statistics
HTML = 29 times
Online first   = 4 times
Total   = 4 times