Welcome to the InfoSci Platform
Reference Hub3
The Effect of Good Corporate Governance on Financial Distress in Companies Listed in Sharia Stock Index Indonesia: Machine Learning Approach

The Effect of Good Corporate Governance on Financial Distress in Companies Listed in Sharia Stock Index Indonesia: Machine Learning Approach

Sylva Alif Rusmita, Moh.Saifin Ami An-Nafis, Indria Ramadhani, Mohammad Irfan
Copyright: © 2023 |Pages: 32
ISBN13: 9781668444832|ISBN10: 1668444836|EISBN13: 9781668444856
DOI: 10.4018/978-1-6684-4483-2.ch014
Cite Chapter Cite Chapter

MLA

Rusmita, Sylva Alif, et al. "The Effect of Good Corporate Governance on Financial Distress in Companies Listed in Sharia Stock Index Indonesia: Machine Learning Approach." Advanced Machine Learning Algorithms for Complex Financial Applications, edited by Mohammad Irfan, et al., IGI Global, 2023, pp. 220-251. https://doi.org/10.4018/978-1-6684-4483-2.ch014

APA

Rusmita, S. A., An-Nafis, M. A., Ramadhani, I., & Irfan, M. (2023). The Effect of Good Corporate Governance on Financial Distress in Companies Listed in Sharia Stock Index Indonesia: Machine Learning Approach. In M. Irfan, M. Elhoseny, S. Kassim, & N. Metawa (Eds.), Advanced Machine Learning Algorithms for Complex Financial Applications (pp. 220-251). IGI Global. https://doi.org/10.4018/978-1-6684-4483-2.ch014

Chicago

Rusmita, Sylva Alif, et al. "The Effect of Good Corporate Governance on Financial Distress in Companies Listed in Sharia Stock Index Indonesia: Machine Learning Approach." In Advanced Machine Learning Algorithms for Complex Financial Applications, edited by Mohammad Irfan, et al., 220-251. Hershey, PA: IGI Global, 2023. https://doi.org/10.4018/978-1-6684-4483-2.ch014

Export Reference

Mendeley
Favorite

Abstract

This study aims to examine the effect of good corporate governance (GCG) on financial distress in companies listed on the Indonesian Sharia Stock Index. The purposive sampling method was used, obtaining 23 samples that met the criteria. Panel regression and machine learning were used to test the hypothesis. Based on the results, the variables of GCG, which consist of institutional ownership (IO), managerial ownership (MO), board of commissioners size (BoC), and proportion of independent commissioners (PI), affect financial distress simultaneously, whereas BoC and PI are partially the most significant variables. The machine learning method shows that extra trees is the best model to analyze financial distress. The model indicates the most significant variable is IO, followed by BoC and PI. From the result, Islamic issuers should manage their GCG by reducing the number of BoC, IO, and adding a proportion of PI to minimize the case of financial distress.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.