ANALYSIS OF THE RELATIVE INFLUENCE OF ESG ISSUES ON THE PROFITABILITY OF MINING COMPANIES IN INDONESIA BY USING ARTIFICIAL NEURAL NETWORK METHOD (ANN)
Sustainable Development Goals that have been standardized into ESG are currently the focus of all stakeholders that are taken into consideration in investment. This study aims to identify the significant relationships between ESG issues and profitability (Return On Assets) of mining companies in...
Saved in:
Main Author: | |
---|---|
Format: | Final Project |
Language: | Indonesia |
Online Access: | https://digilib.itb.ac.id/gdl/view/85457 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Institut Teknologi Bandung |
Language: | Indonesia |
Summary: | Sustainable Development Goals that have been standardized into ESG are
currently the focus of all stakeholders that are taken into consideration in
investment. This study aims to identify the significant relationships between ESG
issues and profitability (Return On Assets) of mining companies in Indonesia, as
well as the hierarchy of their influence contributions. Data on ESG issues and
profitability (Return on Assets) over 8 years (2015-2022) from 7 mineral and coal
mining companies were obtained from Bloomberg and analyzed using Pearson
Correlation, Multiple Linear Regression, and Artificial Neural Network. The
results of the study include: (A) The issues identified as having a significant
relationship on profitability (Return on Assets) of mining companies in Indonesia
are air quality, ecological impact, energy management, GHG emissions
management, ethics & compliance, occupational health & safety management, &
executive compensation, are positively correlated with ROA; (B) The hierarchy of
the influence contributions of ESG issue as mentioned in point A, is (1) Ethics &
Compliance, (2) Executive Compensation, (3) Occupational Health & Safety
Management, (4) Ecological Impact, (5) GHG Emissions Management, (6) Energy
Management, dan (7) Air Quality. The hierarchy of the influence is also validated
using Multiple Linear Regression analysis, specifically for independent variables
that partially have a significant influence. |
---|