Sectoral Analysis of Environment Social and Governance Data Using Deep Learning Model

Sangeetha Rangasamy, Kavitha Rajamohan (), Darpan Deb () and Naga Pillada ()
Additional contact information
Sangeetha Rangasamy: School of Business and Management, CHRIST University Bengaluru, Karnataka 560029, India
Kavitha Rajamohan: ��School of Sciences, CHRIST (Deemed to be University) Bengaluru, Karnataka 560029, India
Darpan Deb: ��School of Sciences, CHRIST (Deemed to be University) Bengaluru, Karnataka 560029, India
Naga Pillada: School of Business and Management, CHRIST University Bengaluru, Karnataka 560029, India

International Journal of Innovation and Technology Management (IJITM), 2024, vol. 21, issue 08, 1-20

Abstract: The relevance of sustainable practices in businesses is indispensable due to the rising global concerns over climate threats and carbon emissions. Integrating Environmental, Social, and Governance (ESG) factors into business models and operations has become the need of the hour. This radical shift in business operations is propelled by the Sustainable Development Goals (SDGs) set up by the United Nations (UN). The advent of newer technologies, especially Machine Learning (ML) and Deep Learning (DL), has aided firms in data assimilation and evaluating their sustainable practices. However, a notable research gap remains in examining ESG integration in the processes and procedures of corporations through AI algorithms. This is due to the challenges of gathering comprehensive ESG-related data and the need for detailed comparative sectoral analysis. The impact and correlation of ESG scores on a firm’s financial performance have been studied, but a sectoral analysis across the globe needs to be done. The use of ML models for the textual and numerical data accumulation analysis is pertinent. The present study aims to provide a data-driven comparative analysis of three chosen sectors with the help of Artificial Intelligence (AI). This research paper focuses on the environmental domain, as the climate threats and opportunities need an appropriate policy for implementation. This study utilizes the vast repository of ESG disclosure data from the Bloomberg database for the energy, consumer durables, and pharmaceutical sectors, covering global and Indian perspectives for comparative analysis. These three sectors provide pivotal data for addressing sustainability challenges regarding the Climate and Emission categories. The research and interpretation of numerical data are done with the help of the DL model and language model Bidirectional Encoder Representations from Transformers (BERT), which analyzes the textual data from social media. The study highlights the challenges associated with ESG integration among the chosen sectors on a global platform. The findings from this study can contribute significantly to the ongoing sustainability dialogue and policy formulation.

Keywords: Climate risk; sustainability; BERT; deep learning; operational policy (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219877024400054
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:ijitmx:v:21:y:2024:i:08:n:s0219877024400054

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219877024400054

Access Statistics for this article

International Journal of Innovation and Technology Management (IJITM) is currently edited by H K Tang

More articles in International Journal of Innovation and Technology Management (IJITM) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().