ESG Volatility Prediction Using GARCH and LSTM Models

Mishra Akshay Kumar (), Kumar Rahul () and Bal Debi Prasad ()
Additional contact information
Mishra Akshay Kumar: Jaipuria Institute of Management, India
Kumar Rahul: Birla Institute of Technology and Science–Pilani (BITS–Pilani), India
Bal Debi Prasad: Birla Institute of Technology and Science–Pilani (BITS–Pilani), India

Financial Internet Quarterly (formerly e-Finanse), 2023, vol. 19, issue 4, 97-114

Abstract: This study aims to predict the ESG (environmental, social, and governance) return volatility based on ESG index data from 26 October 2017 and 31 March 2023 in the case of India. In this study, we utilized GARCH (Generalized Autoregressive Conditional Heteroskedasticity) and LSTM (Long Short-Term Memory) models for forecasting the return of ESG volatility and to evaluate the model’s suitability for prediction. The study’s findings demonstrate the GARCH effect inside the ESG return volatility data, indicating the occurrence of volatility in response to market fluctuations. This study provides insight concerning the suitability of models for volatility predictions. Moreover, based on the analysis of the return volatility of the ESG index, the GARCH model is more appropriate than the LSTM model.

Keywords: ESG Volatility; GARCH; LSTM model (search for similar items in EconPapers)
JEL-codes: C53 D53 G34 O13 (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.2478/fiqf-2023-0029 (text/html)

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:vrs:finiqu:v:19:y:2023:i:4:p:97-114:n:3

DOI: 10.2478/fiqf-2023-0029

Access Statistics for this article

Financial Internet Quarterly (formerly e-Finanse) is currently edited by Tomasz Skica

More articles in Financial Internet Quarterly (formerly e-Finanse) from Sciendo
Bibliographic data for series maintained by Peter Golla ().